Paper Digest: SIGGRAPH 2026 Papers & Highlights
SIGGRAPH (Special Interest Group on Computer GRAPHics and Interactive Techniques) is the annual conference on computer graphics (CG) convened by the ACM SIGGRAPH organization, and deemed as one of the top computer graphics conferences in the world. To help the community quickly catch up on the work presented in this conference, Paper Digest Team processed all accepted papers, and generated one highlight sentence (typically the main topic) for each paper. Readers are encouraged to read these machine generated highlights to quickly get the main idea of each paper.
Search within SIGGRAPH-2026
Literature review on a topic
Generate a written review of SIGGRAPH-2026 research on any topic, with each claim cited to specific papers.
Browse & explore
Browse ~ 1,500 authors (SIGGRAPH-2026), or explore the “Best Paper” Digest listing the most influential SIGGRAPH papers of recent years.
Since 2018, Paper Digest has built a foundation of data spanning decades of conferences, journals, and research topics. The platform features a daily digest service that sifts through tens of thousands of new papers, clinical trials, news articles, and community posts, filtering the noise to highlight what matters most to specific interests. Beyond daily updates, dozens of built-in research tools streamline the academic workflow, supporting efficient reading and writing, comprehensive literature reviews, and automated research report generation.
Paper Digest Team
New York City, New York, 10017
team@paperdigest.org
TABLE 1: Paper Digest: SIGGRAPH 2026 Papers & Highlights
| Paper | Author(s) | |
|---|---|---|
| 1 | Nexus: Native Mesh Generation with Diffusion Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this paper, we present Nexus, a diffusion method that achieves holistic mesh generation via decoupled vertex and topology generation. |
Hanxiao Wang; Ying-Tian Liu; Yuan-Chen Guo; Qi-Yuan Feng; Zi-Xin Zou; Ding Liang; Biao Zhang; Yan-Pei Cao; |
| 2 | SynthVerse: A Large-Scale Diverse Synthetic Dataset for Point Tracking Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: To this end, we introduce SynthVerse, a large-scale, diverse synthetic dataset specifically designed for point tracking. |
Weiguang Zhao; Haoran Xu; Xingyu Miao; Qin Zhao; Rui Zhang; Kaizhu Huang; Ning Gao; Peizhou Cao; Mingze Sun; Mulin Yu; Tao Lu; Linning Xu; Junting Dong; Jiangmiao Pang; |
| 3 | Policy-based Foveated Imaging and Perception Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this work, we introduce a real-time, predictive, and task-aware foveated imaging system that operates directly at image acquisition time. |
Howard Xiao; Jan Ackermann; Boyang Deng; Gordon Wetzstein; |
| 4 | SCOPE: Scale-Consistent One-Pass Estimation of 3D Geometry Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We present SCOPE (Scale-Consistent One-Pass Estimation of 3D Geometry), a novel approach for estimating 3D geometry from extended monocular video sequences, where existing methods struggle to maintain both geometric accuracy and temporal consistency across hundreds of frames. |
Zheng Zhang; Lihe Yang; Tianyu Yang; Chaohui Yu; Yixing Lao; Xiaoyang Guo; Biao Gong; Fan Wang; Hengshuang Zhao; |
| 5 | Audio-Omni: Extending Multi-modal Understanding to Versatile Audio Generation and Editing Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: While some pioneering works have explored unifying audio understanding and generation, they often remain confined to specific domains. To address this, we introduce Audio-Omni, the first end-to-end framework to unify generation and editing across general sound, music, and speech domains, with integrated multi-modal understanding capabilities. |
Zeyue Tian; Binxin Yang; Zhaoyang Liu; Jiexuan Zhang; Ruibin Yuan; Hubery Yin; Qifeng Chen; Chen Li; Jing Lyu; Wei Xue; Yike Guo; |
| 6 | ShapeUP: Scalable Image-Conditioned 3D Editing Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this work, we present ShapeUP, a scalable, image-conditioned 3D editing framework that formulates editing as a supervised latent-to-latent translation within a native 3D representation. |
Inbar Gat; Dana Cohen Bar; Guy Levy; Elad Richardson; Daniel Cohen Or; |
| 7 | EasyVFX: Frequency-Driven Decoupling for Resource-Efficient VFX Generation Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this paper, we introduce EasyVFX, a resource-efficient framework that achieves realistic VFX synthesis under stringent constraints. |
Yue Ma; Xu Ye; Qinghe Wang; Yucheng Wang; Hongyu Liu; Yinhan Zhang; Xinyu Wang; Yuanpeng Chen; Shanhui Mo; Paul Liang; Fangneng Zhan; Qifeng Chen; |
| 8 | R-DMesh: Video-Guided 3D Animation Via Rectified Dynamic Mesh Flow: R-DMesh Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Naively forcing a mesh to follow a mismatched trajectory inevitably leads to severe geometric distortion or animation failure. To address this, we present Rectified Dynamic Mesh (R-DMesh), a unified framework designed to generate high-fidelity 4D meshes that are “rectified” to align with video context. |
Zijie Wu; Lixin Xu; Puhua Jiang; Sicong Liu; Chunchao Guo; Xiang Bai; |
| 9 | CasLayout: Cascaded 3D Layout Diffusion for Indoor Scene Synthesis with Implicit Relation Modeling Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Inspired by human design cognition, we present CasLayout, a cascaded diffusion framework that decomposes the joint scene generation task into four conditional sub-stages with explicit physical and semantic roles: (1) predicting furniture quantity and categories, (2) refining object sizes and feature embeddings, (3) modeling spatial relationships in a latent space, and (4) generating Oriented Bounding Boxes (OBBs). |
Yingrui Wu; You-Kang Kong; Mingyang Zhao; Weize Quan; Dongmin Yan; Yang Liu; |
| 10 | Autoregressive Diffusion with Hybrid Representation for Interactive Human Motion Generation Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Conversely, existing online methods enable real-time synthesis but often sacrifice controllability or struggle with complex text semantics and long-horizon goals due to limited context windows. In this work, we introduce ARDY, a streaming generation framework that bridges this gap by enabling high-fidelity motion generation controllable via online text prompts and flexible kinematic constraints. |
Kaifeng Zhao; Mathis Petrovich; Haotian Zhang; Tingwu Wang; Siyu Tang; Davis Rempe; |
| 11 | SMP: Reusable Score-Matching Motion Priors for Physics-Based Character Control Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this work, we present Score-Matching Motion Priors (SMP), which leverages pre-trained motion diffusion models and score distillation sampling (SDS) to create reusable task-agnostic motion priors. |
Yuxuan Mu; Ziyu Zhang; Yi Shi; Dun Yang; Minami Matsumoto; Kotaro Imamura; Guy Tevet; Chuan Guo; Michael Taylor; Chang Shu; Pengcheng Xi; Xue Bin Peng; |
| 12 | On-the-fly Repulsion in The Contextual Space for Rich Diversity in Diffusion Transformers Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In contrast, acting on spatially-committed intermediate latents tends to disrupt the forming visual structure, leading to artifacts.In this work, we propose to apply repulsion in the Contextual Space as a novel framework for achieving rich diversity in Diffusion Transformers. |
Omer Dahary; Benaya Koren; Daniel Garibi; Daniel Cohen-Or; |
| 13 | GPC: Large-Scale Generative Pretraining for Transferable Motor Control Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this work, we introduce Generative Pretrained Controllers (GPC), which leverage tokenization and next-token modeling to create general-purpose, reusable generative controllers from large-scale motion datasets. |
Yi Shi; Yifeng Jiang; Chen Tessler; Xue Bin Peng; |
| 14 | BFS: Back-to-Front Layered Image Synthesis Via Knowledge Transfer Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this paper, we propose BFS, a novel generation-based framework for layered image synthesis. |
Kyoungkook Kang; Gyujin Sim; Sunghyun Cho; |
| 15 | Surface Reconstruction from Unoriented Points Via Green’s 3rd Identity Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: While recent winding-number-based approaches, such as Parametric Gauss Reconstruction (PGR) and Anisotropic Gauss Reconstruction (AGR), provide elegant implicit formulations, they often suffer from underdetermined or ill-conditioned linear systems. In this work, we analyze the theoretical root of this instability: the winding number formula is oblivious to a broad family of tangential perturbations of the normal field, which introduces a non-trivial nullspace in the resulting integral equations. |
Zhonghao Wu; Dong Xiao; Renjie Chen; |
| 16 | Garment Particles: A 2D–3D Symmetric Garment Representation for Generation and Editing Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: To support both ends of the spectrum, we propose Garment Particles, a 5D point-cloud representation that jointly encodes 2D sewing patterns and 3D geometry. |
Kiyohiro Nakayama; I-Chao Shen; Ruofan Liu; Yiming Wang; Gordon Wetzstein; Takeo Igarashi; |
| 17 | Generative 3D Gaussians with Learned Density Control Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We present Density-Sampled Gaussians (DeG), a novel 3D representation designed to bridge the gap between adaptive rendering primitives and scalable generative modeling. |
Runjie Yan; Yan-Pei Cao; Peng Wang; Ding Liang; Yuan-Chen Guo; |
| 18 | PQ-Free HD: Priority-Queue-Free Hausdorff Distance for Triangle Meshes on GPU Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Our work provides a new method for high-throughput, tolerance-controllable B&B-based geometric queries on GPUs. |
Zhihao Hu; Renjie Chen; |
| 19 | Just-Dub-It: Video Dubbing Via Joint Audio-Visual Diffusion Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this work, we introduce a single-model approach that adapts a foundational audio-video diffusion model for video-to-video dubbing via a lightweight LoRA. |
Anthony Chen; Naomi Ken Korem; Tavi Halperin; Matan Ben Yosef; Urska Jelercic; Ofir Bibi; Or Patashnik; Daniel Cohen-Or; |
| 20 | MV-S2V: Multi-View Subject-Consistent Video Generation Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this work, we propose and address the challenging Multi-View S2V (MV-S2V) task, which synthesizes videos from multiple reference views to enforce 3D-level subject consistency. |
Ziyang Song; Xinyu Gong; Bangya Liu; Zelin Zhao; |
| 21 | MACE-Dance: Motion-Appearance Cascaded Experts for Music-Driven Dance Video Generation Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Accordingly, we present MACE-Dance, a music-driven dance video generation framework with cascaded Mixture-of-Experts (MoE). |
Kaixing Yang; Jiashu Zhu; Xulong Tang; Ziqiao Peng; Xiangyue Zhang; Puwei Wang; Jiahong Wu; Xiangxiang Chu; Hongyan Liu; Jun He; |
| 22 | LoBoFit: Flexible Garment Refitting Via Local Bone Mapping Blending Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We identify that a fundamental limitation lies in the representation: deforming garments directly in global coordinates couples vertices non-locally, creating a complex and poorly-structured optimization landscape. Therefore, we introduce LoBoFit, a robust refitting method built upon a novel Local Bone Mapping Blending (LoBoMap Blending) representation. |
Meng Zhang; Yu Xin; Feiya Guo; Kaizhang Kang; Mengyu Chu; Ruizhen Hu; |
| 23 | AGILE: Hand-object Interaction Reconstruction from Video Via Agentic Generation Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: However, current methods face two prohibitive barriers: (1) reliance on neural rendering often yields fragmented, non-simulation-ready geometries under heavy occlusion, and (2) dependence on brittle Structure-from-Motion (SfM) initialization leads to frequent failures on in-the-wild footage. To overcome these limitations, we introduce AGILE, a robust framework that shifts the paradigm from reconstruction to agentic generation for interaction learning. |
Jin-Chuan Shi; Binhong Ye; Tao Liu; Xiaoyang Liu; Yangjinhui Xu; Junzhe He; Zeju Li; Hao Chen; Chunhua Shen; |
| 24 | Distance Field Rasterization for End-to-End Mesh Reconstruction Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In contrast, implicit signed distance field (SDF) methods provide well-defined surfaces but are typically optimized with computationally expensive ray marching. We propose SDFRaster, a rasterizable SDF representation that bridges this gap by combining the efficiency of rasterization with signed distance field for end-to-end mesh reconstruction. |
Jinkai Cui; Kaiwen Song; Chumeng Niu; Juyong Zhang; |
| 25 | ViewWeaver: Geometry-Grounded Generative Rendering for 3D-Aware Image Customization Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We propose ViewWeaver, a geometry-grounded generative rendering framework that anchors synthesis with explicit target-view rendering cues aligned with camera geometry, and aggregates multi-view evidence through a lightweight Mixture-of-Views module inside a rectified-flow DiT generator. |
Yaowei Li; Xiaoyu Li; Zhaoyang Zhang; Hongxiang Li; Long Chen; Ying Shan; Yuexian Zou; |
| 26 | Robust Computation of Boundary Path Integrals Using Kernel-Density Estimation Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Although their mathematical formulation is well established, designing efficient and robust numerical estimators remains challenging. Most state-of-the-art boundary sampling methods rely on primary-sample-space guiding, which tends to break down on finely tessellated geometries; reparameterization-based alternatives, meanwhile, often incur high variance and/or significant computational overhead.In this paper, we introduce a simple, robust, and consistent solution to this problem. |
Peiyu Xu; Lifan Wu; Benedikt Bitterli; Ravi Ramamoorthi; Shuang Zhao; |
| 27 | Faster 3D Gaussian Splatting Convergence Via Structure-Aware Densification Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We present a structure-aware densification framework. Our key insight is that the decision to subdivide a Gaussian should be driven by an explicit comparison between its projected screen-space extent and the local structure of the texture it seeks to represent. |
Linjie Lyu; Ayush Tewari; Jianchun Chen; Thomas Leimkuehler; Christian Theobalt; |
| 28 | Generalizable and Relightable Gaussian Splatting for Human Novel View Synthesis Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We propose GRGS, a generalizable and relightable 3D Gaussian framework for high-fidelity human novel view synthesis under diverse lighting conditions. |
Yipengjing Sun; Shengping Zhang; Chenyang Wang; Shunyuan Zheng; Zonglin Li; Xiangyang Ji; |
| 29 | SegviGen: Repurposing 3D Generative Model for Part Segmentation Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We introduce SegviGen, a framework that repurposes native 3D generative models for 3D part segmentation. |
Lin Li; Haoran Feng; Zehuan Huang; Haohua Chen; Wenbo Nie; Shaohua Hou; Keqing Fan; Pan Hu; Sheng Wang; Buyu Li; Lu Sheng; |
| 30 | Spatiotemporal FLIP for Fast Free-Surface and Two-Phase Simulation With Very Large Time Steps Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We present ST-FLIP, a spatiotemporal extension of the Fluid-Implicit Particle (FLIP) method for incompressible free-surface and two-phase liquid simulation. |
Bernhard Braun; Rene Winchenbach; Jan Bender; Nils Thuerey; |
| 31 | Pixal3D: Pixel-Aligned 3D Generation from Images Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We argue this stems from an implicit 2D-3D correspondence issue: most 3D-native generators synthesize shape in canonical space and inject image cues via attention, leaving pixel-to-3D associations ambiguous. To tackle this issue, we draw inspiration from 3D reconstruction and propose Pixal3D, a pixel-aligned 3D generation paradigm for high-fidelity 3D asset creation from images. |
Dong-Yang Li; Wang Zhao; Yuxin Chen; Wenbo Hu; Meng-Hao Guo; Fang-Lue Zhang; Ying Shan; Shi-Min Hu; |
| 32 | Nonlinear Multigrid for Injective Embedding Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this work, we propose a Nonlinear Multigrid (MG/Opt) framework specifically tailored for efficient TLC energy minimization. |
Yu Zhao; Renjie Chen; |
| 33 | TrajVG: 3D Trajectory-Coupled Visual Geometry Learning Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We propose TrajVG, a reconstruction framework that makes cross-frame 3D correspondence an explicit prediction by estimating camera-coordinate 3D trajectories. |
Xingyu Miao; Weiguang Zhao; Tao Lu; Linning Xu; Mulin Yu; Yang Long; Jiangmiao Pang; Junting Dong; |
| 34 | AniGen: Unified S3 Fields for Animatable 3D Asset Generation Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We present AniGen, a unified framework that directly generates animate-ready 3D assets conditioned on a single image. |
Yi-Hua Huang; Zi-Xin Zou; Yuting He; Chirui Chang; Cheng-Feng Pu; Ziyi Yang; Yuan-Chen Guo; Yan-Pei Cao; Xiaojuan Qi; |
| 35 | ACT: A Unified Framework for Rigging and Animating Characters with Arbitrary Topologies Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Traditional pipelines fracture this process into sequential stages—rigging, skinning, and motion synthesis—ignoring the inherent coupling between morphological structure and motor function. To bridge this gap, we introduce ACT, a unified generative framework that reformulates rigging and animation not as independent tasks, but as complementary views of a single hyper-kinematic process.Our key insight is to model the joint distribution of skeletal topology and temporal motion within a shared latent space. |
Pengyu Long; Weirui Wang; Qingcheng Zhao; Xiaoyang Guo; Xiaoyu Pan; Qixuan Zhang; Jiaqing Zhou; Tianlei Hu; Wei Yang; Lan Xu; Jingyi Yu; |
| 36 | ReRoPE: Repurposing RoPE for Relative Camera Control Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We introduce ReRoPE, a plug-and-play framework that incorporates relative camera information into pre-trained video diffusion models without compromising their generation capability. |
Chunyang Li; Yuanbo Yang; Jiahao Shao; Hongyu Zhou; Katja Schwarz; Yiyi Liao; |
| 37 | HoloPathTracer: Fast and Accurate Wave Path Tracing for Holography Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Specifically, we employ a Monte Carlo method to solve both the rendering equation and the Rayleigh-Sommerfeld integral simultaneously. |
Wenbin Zhou; Xiangyu Meng; Jiankai Xing; Xin Liu; Suyeon Choi; Yifan Peng; |
| 38 | Diceplay: A Modular Canvas for Physical Image Composition Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We present Diceplay, a modular physical display for abstract visual composition built from a grid of identical dice. |
Milin Kodnongbua; Zihan Jack Zhang; Shishi Xiao; Vivian Li; Heather Robertson; Rulin Chen; David Laidlaw; Adriana Schulz; |
| 39 | VidSplat: Gaussian Splatting Reconstruction with Geometry-Guided Video Diffusion Priors Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Although recent efforts alleviate this issue by enhancing multi-view consistency to produce plausible surfaces, they struggle to infer unseen, occluded, or weakly constrained regions beyond the input coverage. To address this limitation, we present VidSplat, a training-free generative reconstruction framework that leverages powerful video diffusion priors to iteratively synthesize novel views that compensate for missing input coverage, and thereby recover complete 3D scenes from sparse inputs. |
Jimin Tang; Wenyuan Zhang; Junsheng Zhou; Zian Huang; Kanle Shi; Shenkun Xu; Yu-Shen Liu; Zhizhong Han; |
| 40 | Video Analysis and Generation Via A Semantic Progress Function Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Transformations produced by image and video generation models often evolve in a highly non-linear manner: long stretches where the content barely changes are followed by sudden, abrupt semantic jumps. To analyze and correct this behavior, we introduce a Semantic Progress Function, a one-dimensional representation that captures how the meaning of a given sequence evolves over time. |
Gal Metzer; Sagi Polaczek; Ali Mahdavi-Amiri; Raja Giryes; Daniel Cohen-Or; |
| 41 | B-repLer: Language-guided Editing of CAD Models Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We present B-repLer, a novel framework that directly connects natural language with editing CAD models by operating in a learned latent space. |
Yilin Liu; Niladri Shekhar Dutt; Changjian Li; Niloy J. Mitra; |
| 42 | Retrofitting Existing 3D Objects with Surface-Conforming Capacitive Sensing Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this paper, we present a computational fabrication pipeline that retrofits surface-only sensor layouts to 3D geometries for multi-touch interaction. |
Andela Ilic; Junpeng Gao; Zhipeng Li; Yijing Jiang; Rachel Schuchert; Manuel Meier; Philipp Herholz; Christian Holz; |
| 43 | Mobile3DGS3: Accelerate Mobile 3DGS Rendering Via Gradient-Aware Super-Sampling and Frame Interpolation Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We propose Mobile3DGS3, a lightweight framework that alternates between super-sampling and frame interpolation. |
Fan Gao; YIbo Zhao; Changhao Song; Jiarui Wen; Yuxuan Song; Youcheng Cai; Ligang Liu; |
| 44 | A Bayesian Approach for Task-Specific Next-Best-View Selection with Uncertain Geometry Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We develop a framework for task-specific active next-best-view selection in 3D reconstruction from point clouds, by casting the problem in the language of Bayesian decision theory. |
Jingsen Zhu; Silvia Sell\'{a}n; Alexander Terenin; |
| 45 | Canvas-to-Image: Compositional Image Generation with Multimodal Controls Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: While modern diffusion models excel at generating high-quality and diverse images, they still struggle with high-fidelity compositional and multimodal control, particularly when users simultaneously specify text prompts, subject references, spatial arrangements, pose constraints, and layout annotations. We introduce Canvas-to-Image , a unified framework that consolidates these heterogeneous controls into a single canvas interface, enabling users to generate images that faithfully reflect their intent. |
Yusuf Dalva; Gordon Guocheng Qian; Maya Goldenberg; Tsai-Shien Chen; Kfir Aberman; Sergey Tulyakov; Pinar Yanardag; Kuan-Chieh Jackson Wang; |
| 46 | LooseRoPE: Content-aware Attention Manipulation for Semantic Harmonization Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We observe that attention maps in diffusion-based editing models inherently govern whether image regions are preserved or adapted for coherence. Building on this insight, we introduce LooseRoPE, a saliency-guided modulation of rotational positional encoding (RoPE) that loosens the positional constraints to continuously control the attention field of view. |
Etai Sella; Yoav Baron; Hadar Averbuch-Elor; Daniel Cohen-Or; Or Patashnik; |
| 47 | Real-Time Level-of-Detail Rendering with ReSTIR Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this paper, we introduce a surface point mapping that enables sample reuse across frames containing meshes with different topologies. |
Yu-Chen Wang; Markus Kettunen; Daqi Lin; Chris Wyman; Lifan Wu; Shuang Zhao; |
| 48 | VecSet-Edit: Unleashing Pre-trained LRM for Mesh Editing from Single Image Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Prior attempts, such as VoxHammer, rely on voxel-based representations that suffer from limited resolution and necessitate labor-intensive 3D masks. To address these limitations, we propose VecSet-Edit, the first pipeline that leverages the high-fidelity VecSet Large Reconstruction Model (LRM) as a backbone for mesh editing. |
Teng-Fang Hsiao; Bo-Kai Ruan; Yu-Lun Liu; Hong-Han Shuai; |
| 49 | MOCHI: Motion Enhancement of Collaborative Human-object Interactions Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Such complexity leads to noisy MHOI captures characterized by several artifacts: contact misalignment between hands and objects, motion jitter and temporal inconsistencies in the captured sequences, and missing or incomplete finger-level articulation details. To address these challenges, we present MOCHI (MOtion Enhancement of Collaborative Human-object Interactions), a two-stage framework for enhancing noisy MHOI data. |
Jiye Lee; Yonghun Choi; Jungdam Won; |
| 50 | Sketch2Arti: Sketch-based Articulation Modeling of CAD Objects Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this paper, we present Sketch2Arti, the first sketch-based articulation modeling system for CAD objects. |
Yi Yang; Hao Pan; Yijing Cui; Alla Sheffer; Changjian Li; |
| 51 | Boundary-aware Neural Model Reduction for PDEs Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this work, we focus on Laplace-type operators and extend shape space neural eigenanalysis to handle boundary conditions beyond natural Neumann settings. |
Li Liao; Pengfei Shen; Yifan Peng; |
| 52 | Fast and Exact Winding Numbers for Triangle Meshes Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We revisit the computation of 3D generalized winding numbers, a useful measure for inside-outside classification on triangle meshes with gaps, self-intersections, and open boundaries. |
Peiyuan Xie; Christian Hafner; Chris Wojtan; |
| 53 | Continuous Control of Editing Models Via Adaptive-Origin Guidance Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We attribute this behavior to the unconditional prediction, which serves as the guidance origin and dominates the generation at low guidance scales, while representing an arbitrary manipulation of the input content. To enable continuous control, we introduce Adaptive-Origin Guidance (AdaOr), a method that adjusts this standard guidance origin with an identity-conditioned adaptive origin, using an identity instruction corresponding to the identity manipulation. |
Alon Wolf; Chen Katzir; Kfir Aberman; Or Patashnik; |
| 54 | MPM Lite: Linear Kernels and Integration Without Particles Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We introduce MPM Lite, a hybrid Lagrangian/Eulerian method that eliminates the need for particle-based quadrature at solve time. |
Xiang Feng; Yunuo Chen; Chang Yu; Hao Su; Demetri Terzopoulos; Yin Yang; Joe Masterjohn; Alejandro Castro; Chenfanfu Jiang; |
| 55 | VFXMaster: Unlocking Dynamic Visual Effect Generation Via In-Context Learning Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Prevailing methods often rely on the one-LoRA-per-effect paradigm, which is resource-intensive and fundamentally incapable of generalizing to unseen effects, thus limiting scalability and creation. To address this challenge, we introduce VFXMaster, a unified, reference-based framework for VFX video generation. |
BaoLu Li; Yiming Zhang; Qinghe Wang; Liqian Ma; Xiaoyu Shi; Xintao Wang; Pengfei Wan; Zhenfei Yin; Yunzhi Zhuge; Huchuan Lu; Xu Jia; |
| 56 | Multi-Agent CAD Code Generation Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We present CAD-Factory, a Text-to-CAD generation system for language-driven CAD modeling that explicitly models the structural and parametric semantics of CAD programs. |
Yang Liu; Daxuan Ren; Yijie Ding; Jianmin Zheng; Fang Deng; |
| 57 | TopoCap: Learning Topology-Agnostic Motion Priors for Monocular Video-to-Animation Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We introduce TopoCap, the first unified framework capable of extracting motion from monocular video and retargeting it onto characters with arbitrary, unseen skeletal topologies, i.e., from bipeds to hexapods and inanimate objects, without test-time optimization. |
Cheng-Feng Pu; Jia-Peng Zhang; Meng-Hao Guo; Yan-Pei Cao; Shi-Min Hu; |
| 58 | Strips As Tokens: Artist Mesh Generation with Native UV Segmentation Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: However, the token ordering strategies employed by existing methods typically fail to meet professional artist standards, where coordinate-based sorting yields inefficiently long sequences, and patch-based heuristics disrupt the continuous edge flow and structural regularity essential for high-quality modeling. To address these limitations, we propose Strips as Tokens (SATO), a novel framework with a token ordering strategy inspired by triangle strips. |
Rui Xu; Dafei Qin; Kaichun Qiao; Qiujie Dong; Huaijin Pi; Qixuan Zhang; Longwen Zhang; Lan Xu; Jingyi Yu; Wenping Wang; Taku Komura; |
| 59 | EchoAvatar: Real-time Generative Avatar Animation from Audio Streams Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this paper, we introduce a novel framework designed to generate continuous, coherent full-body motion from streaming speech and music with low latency. |
Bohong Chen; Yumeng Li; Yinglin Xu; Youyi Zheng; Yanlin Weng; Kun Zhou; |
| 60 | NILE: Nested Interleaving of Low-Dimensional Elements Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Our approach leverages high-dimensional low-discrepancy sequences to orchestrate sample generation by a collection of local samplers operating over power-of-two hierarchical intervals. |
Abdalla Ahmed; Matt Pharr; Victor Ostromoukhov; Hui Huang; |
| 61 | GenPIE: A Time-Resolved Plenoptic Imager Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this work, we present GenPIE, a Generative Plenoptic Imager designed to bridge the gap between sparse physical observations and high-dimensional light transport. |
Ziheng Wang; Siyuan Shen; Huanyu Xu; Kaichun Qiao; Longwen Zhang; Qixuan Zhang; Qilin Sun; Shiying Li; Jingyi Yu; |
| 62 | Interactive Yarn-level Knitwear with Nested Douglas-Rachford Splitting Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: This paper proposes a novel simulation framework designed to enhance the performance and stability for numerical simulation of nonlinear, non-convex, and high-resolution knitwear. |
Chun Yuan; Zixuan Lu; Haoyang Shi; Dewen Guo; Huamin Wang; Chenfanfu Jiang; Zherong Pan; Kui Wu; Yin Yang; |
| 63 | SmoothMotionVectors: Optimizing Your Content for Video Codecs in Free View Video Compression Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We present an empirical study of free-view video compression for dynamic scenes reconstructed with 3D Gaussian Splatting, examining how practical pipeline design choices affect reconstruction fidelity and storage efficiency. |
Mingyang Song; Yang Zhang; Siyu Tang; Tun\c{c} Ozan Ayd\i{}n; |
| 64 | Semantic-Structural Alignment for Generative Pictorial Charts Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We present a generative framework for the automated synthesis of pictorial charts that bridges the gap between semantic expression and structural faithfulness. |
Zhida Sun; Yulin Zhang; Zheng Gu; Min Lu; Bongshin Lee; Daniel Cohen-Or; Hui Huang; |
| 65 | Computational Design of Coordinate-Motion Assemblies Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Building on this theory, we introduce a two-stage algorithm that optimizes contact interfaces for a target motion and constructs physically feasible part geometries that conform to a user-specified global shape. |
Yukun Lu; Ke Chen; Ligang Liu; Peng Song; |
| 66 | PEGAsus: 3D Personalization of Geometry and Appearance Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We present PEGAsus, a new framework capable of generating Personalized 3D shapes by learning shape concepts at both Geometry and Appearance levels. |
Jingyu Hu; Bin Hu; Ka-Hei Hui; Haipeng Li; Zhengzhe Liu; Daniel Cohen-Or; Chi-Wing Fu; |
| 67 | DissolveStereo: Coarse Depth Injection for Zero-Shot Stereo Video Generation Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We introduce DissolveStereo, a novel framework for zero-shot stereo video generation that leverages video diffusion priors without requiring paired training data. |
Jian Shi; Qian Wang; Zhenyu Li; Wenqing Cui; Ramzi Idoughi; Peter Wonka; |
| 68 | Streaming of Rendered Content with Adaptive Frame Rate and Resolution Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this work, we exploit the spatio-temporal limits of the human visual system to improve perceived quality while reducing rendering costs by adaptively adjusting both frame rate and resolution based on scene content and motion. |
Yaru Liu; Joseph G. March; Rafa\l{} K. Mantiuk; |
| 69 | AMOR: Airborne Motion Reconstruction Via Homotopy-Aware Trajectory Optimization Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We propose a novel method for reconstructing 3D airborne motion by refining inaccurate estimates produced by state-of-the-art HMR systems. |
Chanha Kim; Jungdam Won; |
| 70 | Motion4Motion: Motion Transfer Across Subjects at Inference Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this paper, we jump out of the skeleton-based motion transfer framework and propose a training-free motion transfer framework, named Motion4Motion. |
Ling-Hao Chen; Zixin Yin; Duomin Wang; Xianfang Zeng; Gang Yu; |
| 71 | MpcGear: Multi-Point Conjugation Gear Mechanisms Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this paper, we present a new gear mechanism called the multi-point conjugation gear mechanism for exactly generating a user-specified 3D motion under external loads. |
Ke Chen; Joshua John Shi Kai Lee; Jianmin Zheng; Ligang Liu; Peng Song; |
| 72 | VeraRetouch: A Lightweight Fully Differentiable Framework for Multi-Task Reasoning Photo Retouching Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: However, existing approaches often rely on non-differentiable external software, creating optimization barriers and suffering from high parameter redundancy and limited generalization. To address these challenges, we propose VeraRetouch, a lightweight and fully differentiable framework for multi-task photo retouching. |
Yihong Guo; Youwei Lyu; Jiajun Tang; Yizhuo Zhou; Hongliang Wang; Jinwei Chen; Changqing Zou; Qingnan Fan; |
| 73 | Stroke of Surprise: Progressive Semantic Illusions in Vector Sketching Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this work, we introduce Progressive Semantic Illusions, a novel vector sketching task where a single sketch undergoes a dramatic semantic transformation through the sequential addition of strokes. |
Huai-Hsun Cheng; Siang-Ling Zhang; Yu-Lun Liu; |
| 74 | LongE2V: Long-Horizon Event-based Video Reconstruction, Prediction, and Frame Interpolation with Video Diffusion Models Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We propose LongE2V, a novel approach that leverages pre-trained video diffusion priors to jointly handle event-based video reconstruction, prediction, and frame interpolation. |
Cheng-De Fan; Chun-Wei Tuan Mu; Chen-Wei Chang; Chin-Yang Lin; Kun-Ru Wu; Yu-Chee Tseng; Yu-Lun Liu; |
| 75 | Shellular Metamaterial Design Via Compact Electric Potential Parametrization Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We present a compact yet highly expressive design space for shellular metamaterials that support both interactive exploration and inverse design. |
Tianyi Huang; Chang Liu; Bohan Wang; |
| 76 | PatternGSL: A Structured Specification Language for Template-Free and Simulation-Ready 3D Garments Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We present PatternGSL, a structured garment representation in the form of a template-free and learnable specification language that encodes complete sewing patterns, including panel boundaries, parameterized seams, and explicit stitch topology, in a compact and standardized form. |
Zhenyang Li; Lutao Jiang; Yizhou Zhao; Ying-Cong Chen; Xin Wang; Weikai Chen; Yifan Peng; |
| 77 | A Few-Step Generative Model on Cumulative Flow Maps Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We propose a unified, few-step generative modeling framework based on cumulative flow maps for long-range transport in probability space, inspired by flow-map techniques for physical transport and dynamics. |
Zhiqi Li; Duowen Chen; Yuchen Sun; Bo Zhu; |
| 78 | 2D Gaussian Splatting for B\'{e}zier Spline Line Art Vectorization Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this paper, we leverage several recent advances in the field to introduce a new state-of-the-art method for line art vectorization. |
Tianhao Chen; Clara Fernandez; Marteinn Oskarsson; Chuck Tappan; Olga Sorkine-Hornung; Markus Gross; Christopher Schroers; Abdelaziz Djelouah; |
| 79 | C0 Generalized Coons Volumes Over Arbitrary Polyhedra Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this paper, we generalize the Coons volume from hexahedral topology to arbitrary polyhedral topologies via generalized barycentric coordinates. |
Kaikai Qin; Zeqi Ge; P\'{e}ter Salvi; Chenhao Ying; Huibiao Wen; Kepeng Xu; Shiqing Xin; Chongyang Deng; |
| 80 | Computational Design of Terrestrial Robots with Anisotropic Friction Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We propose a computational pipeline for co-designing anisotropic friction and controllers of terrestrial robots with diverse morphologies. |
Hang Hu; Kangbo Lyu; Changyu Hu; Zihan Li; Peiwen Yang; Minchen Li; Shuguang Li; Tao Du; |
| 81 | Radiance Caching for Differentiable Path Tracing Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Prior work recently showed that the variance reduction provided by a radiance cache can alleviate these challenges.We revisit the combination of inverse rendering and radiance caching with a twist, by introducing a spatial blending field that locally interpolates between the cache and standard unbiased estimators. Recursive application of this idea yields a rich design space of evaluation strategies and inter-estimator consistency losses; we map this space and identify effective components. |
Ziyi Zhang; Delio Vicini; Sebastian Winberg; Stephan Garbin; Wenzel Jakob; |
| 82 | BoxCtrl: 3D-Aware Visual Prompting for Geometric Image Editing Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: However, achieving precise and consistent geometric image editing, such as translating, scaling and rotating in 3D space, remains a major challenge. In this work, we introduce BoxCtrl, a 3D-aware visual prompting framework to address this problem. |
Feifei Wang; Shiyuan Yang; Xiaoyu Li; Jing Liao; |
| 83 | PointLLM-R: Enhancing 3D Point Cloud Reasoning Via Chain-of-Thought Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this paper, we propose a data-centric framework for constructing large-scale CoT supervision tailored to 3D point cloud understanding. |
Chaoqi Chen; Qile Xu; Wenjun Zhou; Hui Huang; |
| 84 | Non-line-of-sight Imaging with Arbitrary Relay Surface Geometries Via 3D Gaussian Transient Rendering Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Despite impressive progress in time-of-flight (ToF)-based non-line-of-sight (NLOS) imaging, real-world deployment remains challenging because practical measurements are often collected over spatially limited, arbitrarily shaped relay regions—conditions that violate the planar-wall and dense-sampling assumptions made by most existing methods. To address these limitations, we propose a LOS-guided NLOS imaging pipeline that imposes no geometric assumptions on the relay surface and naturally supports both confocal and non-confocal configurations. |
Yi Wang; Ziyu Zhan; Yuran Wang; Hao Wang; Qiang Liu; Zuoqiang Shi; Lingyun Qiu; Xing Fu; |
| 85 | LayerInbetween: Occlusion-Aware Stroke Correspondence and Inbetweening with Automatic Layering Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: To reduce tedious effort, we present LayerInbetween, an occlusion-aware framework for vector stroke correspondence and automatic inbetweening. |
Haoran Mo; Zhongyue Guan; Yixin Hu; Zeyu Wang; |
| 86 | DreamActor-M2: Universal Character Image Animation Via Spatiotemporal In-Context Learning Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Despite recent advancements, existing methods suffer from two fundamental challenges: (1) suboptimal motion injection strategies that lead to a trade-off between identity preservation and motion consistency, manifesting as a see-saw, and (2) an over-reliance on explicit pose priors (e.g., skeletons), which inadequantely capture intricate dynamics and hinder generalization to arbitrary, non-humanoid characters. To address these challenges, we present DreamActor-M2, a universal animation framework that reimagines motion conditioning as an in-context learning problem. |
Mingshuang Luo; Shuang Liang; Zhengkun Rong; Yuxuan Luo; Tianshu Hu; Ruibing Hou; Hong Chang; Yong Li; Yuan Zhang; Mingyuan Gao; |
| 87 | PEAR: Pixel-aligned Expressive HumAn Mesh Recovery Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: These issues make current approaches difficult to apply to downstream tasks. To address these challenges, we propose PEAR—a fast and robust framework for pixel-aligned expressive human mesh recovery. |
Jiahao Wu; Yunfei Liu; Lijian Lin; Ye Zhu; Lei Zhu; Jingyi Li; Yu Li; |
| 88 | Single-View Holographic Volumetric 3D Printing with Coupled Differentiable Wave-Optical and Photochemical Optimization Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We present Single-View Holographic Volumetric Additive Manufacturing (SHVAM), a mechanically static system that shapes volumetric dose distributions using time-multiplexed, phase-only holograms projected from a single optical axis. |
Felix Wechsler; Riccardo Rizzo; Christophe Moser; |
| 89 | VFAvatar: Feed-Forward 3D Avatar Reconstruction from Casual Image Collections Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: While some previous methods circumvent these difficulties by adopting generative approaches like score distillation, they struggle to preserve authentic appearance details from source images. To address these limitations, we introduce Visual-Fusion-Avatar (VFAvatar), a novel feed-forward framework that reconstructs 3D avatars by fusing visual cues in just a few seconds. |
Shuo Huang; Zixuan Wang; Xiaoyu Qin; Shikun Sun; Jiayi Li; Jia Jia; |
| 90 | Inspiration Seeds: Learning Non-Literal Visual Combinations for Generative Exploration Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We propose Inspiration Seeds, a generative framework that shifts image generation from final execution to exploratory ideation. |
Kfir Goldberg; Elad Richardson; Yael Vinker; |
| 91 | Co-Optimization of Structure and Manufacturable Semi-Continuous Layers for Laminated Composites Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: To enable the design and manufacturing of optimized composite structures using fabric plies, we propose a field-driven optimization framework that jointly optimizes structural topology and manufacturable layers. |
Tao Liu; Aoran Lyu; Yongxue Chen; Yu Jiang; Michael James Petty; Charlie C. L. Wang; |
| 92 | Generative Texture Filtering Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We present a generative method for texture filtering, which exhibits surprisingly good performance and generalizability. |
Rongjia Zheng; Shangwei Huang; Lei Zhu; Wei-Shi Zheng; Qing Zhang; |
| 93 | Autoregressive B-Rep Shape Generation with Parametric Surfaces Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We present ParaCAD, an autoregressive framework for point-cloud-conditioned B-Rep generation that directly operates on native parametric surfaces. |
Dafei Qin; Rui Xu; Zeyu Shen; Kaichun Qiao; Hongyang Lin; Qixuan Zhang; Huaijin Pi; Lan Xu; Jingyi Yu; Wenping Wang; Taku Komura; |
| 94 | TSMC: Time-varying 4D Scene Mesh Compression Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Existing mesh compression standards are not well-suited for complex scene meshes with dynamic content, and no standardized encoding techniques have been widely adopted for this class of data. To address this gap, we propose TSMC, a novel compression framework for 3D time-varying scene mesh sequences. |
Guodong Chen; Libor V\'{a}\v{s}a; Amrita Mazumdar; Mallesham Dasari; |
| 95 | Sparse-to-Complete: From Sparse Image Captures to Complete 3D Scenes Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We introduce S2C-3D, a novel sparse-view 3D reconstruction framework for high-fidelity and complete scene reconstruction from as few as six to eight images. |
Yiyang Shen; Yin Yang; Kun Zhou; Tianjia Shao; |
| 96 | Go-with-the-Track: Video Compositing and Motion Control with Point Tracking Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We present Go-with-the-Track, which unifies both capabilities by jointly conditioning on multiple reference images and reference-anchored point-tracks — extending conventional point-tracks to explicitly establish correspondences between generated frames and reference images, thus enabling precise compositing and motion control throughout the video. |
Koichi Namekata; Yash Kant; Zhizheng Liu; Ryan Burgert; Yuancheng Xu; Kuan Heng Lin; Emmett Steven; Julien Philip; Li Ma; Andrea Vedaldi; Paul Debevec; Ning Yu; |
| 97 | M-ABD: Scalable, Efficient, and Robust Multi-Affine-Body Dynamics Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: This paper introduces a novel framework that leverages the linear kinematic mapping of Affine Body Dynamics (ABD). |
Zhiyong He; Dewen Guo; Minghao Guo; Yili Zhao; Wojciech Matusik; Hao Su; Chenfanfu Jiang; Peter Yichen Chen; Yin Yang; |
| 98 | The Antipodal Method: Fast, Accurate, and Robust 3D Generalized Winding Numbers Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Our approach expresses the winding number as the sum of two intuitive geometric quantities: the signed number of ray-surface intersections and a boundary integral over the surface’s projection onto the unit sphere. This insight leads to an efficient discretization that avoids expensive surface integrals and spherical arrangements.For meshes, our method achieves average speedups of 22X on a CPU compared to the fastest precise methods and 3X compared to the fastest approximation method, while maintaining full precision. |
Cedric Martens; Philip Trettner; Mikhail Bessmeltsev; |
| 99 | Uncertainty-aware Geometry Processing on Gaussian Process Implicit Surfaces Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We present a framework for uncertainty-aware geometry processing on Gaussian Process Implicit Surfaces (GPIS), enabling computations directly on such probabilistic representations of shapes. |
Baptiste Genest; David Coeurjolly; |
| 100 | Implicit Surface Compression — with Good Old Discrete Cosine Transform and Motion Compensation Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this paper, we present a novel end-to-end compression framework for dynamic Truncated Signed Distance Field volumes derived from captured 3D content, leveraging a representation that is temporally stable, easily parallelizable, and already widely used in scene reconstruction and volumetric fusion pipelines. |
Tao Jin; Shengxi Wu; Tianshu Huang; Mallesham Dasari; Srinivasan Seshan; Anthony Rowe; |
| 101 | Prox-E: Fine-Grained 3D Shape Editing Via Primitive-Based Abstractions Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: While effective for appearance-based modifications, such 2D-centric 3D editing pipelines often struggle with fine-grained 3D editing, where localized structural changes must be applied while strictly preserving an object’s overall identity. To address this limitation, we propose Prox · E, a training-free framework that enables fine-grained 3D control through an explicit, primitive-based geometric abstraction. |
Etai Sella; Hao Phung; Nitay Amiel; Or Litany; Or Patashnik; Hadar Averbuch-Elor; |
| 102 | MoonSplat: Monocular Online Gaussian Splatting with Sim(3) Global Optimization Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: However, existing online 3DGS methods still suffer from some key challenges: fragile camera pose estimation due to the lack of global optimization, and low optimization efficiency in large-scale or long-sequence scenarios. To address these issues, we propose a robust and efficient online voxelized 3DGS reconstruction framework integrated with global Sim(3) optimization, which enables reliable camera tracking and efficient global loop closure for both camera poses and voxelized 3DGS. |
Guo Pu; Yixuan Han; Haofeng Li; Yao Zhang; Hui Zhou; Zhouhui Lian; |
| 103 | GMT: A Geometric Multigrid Transformer Solver for Microstructure Homogenization Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We introduce GMT, a Geometric Multigrid Transformer – a neural solver with high numerical fidelity for fast and reliable lattice homogenization. |
Yu Xing; Yang Liu; Tianyang Xue; Lin Lu; |
| 104 | CAGS: Color-Adaptive Volumetric Video Streaming with Dynamic 3D Gaussian Splatting Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Our preliminary studies reveal that aggressive attribute compression primarily causes color distortion, which can be effectively corrected in the rendered image using a reference image. Motivated by these findings, we propose a novel Color-Adaptive scheme for adaptive VV streaming that uses vector quantization (VQ) to establish LoDs and correct color distortions with low-resolution reference images. |
Daheng Yin; Yili Jin; Jianxin Shi; Isaac Ding; Miao Zhang; Fangxin Wang; Zhaowu Huang; Cong Zhang; Jiangchuan Liu; Fang Dong; |
| 105 | OmniRoam: World Wandering Via Long-Horizon Panoramic Video Generation Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We propose OmniRoam, a controllable panoramic video generation framework that exploits the rich per-frame scene coverage and inherent long-term spatial and temporal consistency of panoramic representation, enabling long-horizon scene wandering. |
Yuheng Liu; Xin Lin; Xinke Li; Baihan Yang; Chen Wang; Kalyan Sunkavalli; Yannick Hold-Geoffroy; Hao Tan; Kai Zhang; Xiaohui Xie; Zifan Shi; Yiwei Hu; |
| 106 | Learned Universal Interoperable Virtual Try-ON Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We address clothing-to-SMPL using a geometry-driven correspondence model, and introduce a diffusion-based body-to-SMPL correspondence approach that leverages multi-view consistent appearance features together with a pretrained 2D foundation model. |
Cong Cao; Xianhang Cheng; Jingyuan Liu; Yujian Zheng; Zhenhui Lin; Ren Li; Meriem Chkir; Hao Li; |
| 107 | Learning Sewing Patterns Via Latent Flow Matching of Implicit Fields Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this work, we introduce a sewing pattern modeling method based on an implicit representation. |
Cong Cao; Ren Li; Corentin Dumery; Hao Li; |
| 108 | A Nonlocal Unified Variational Framework for Free Surface Flows Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Existing particle-based methods often rely on operator splitting, which introduces coupling artifacts and limits stability. We propose a unified nonlinear optimization framework that achieves a strong coupling of these three effects within a single solver. |
Shusen Liu; Yuzhong Guo; Lixin Ren; Ying Qiao; Xiaowei He; |
| 109 | FabricTryOn: Taming Image Editing Models for Garment Re-Texturing Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: A comprehensive transformation involves both material reflectance and geometric deformation from fabric drape. In this work, we focus on the visual aspects of this challenge and simplify fabric try-on to a re-texturing task that replaces garment materials while preserving the original geometry and illumination. |
Jun Ma; Qian He; Gaofeng He; Huang Chen; Chen Liu; Xiaogang Jin; Yin Yang; Huamin Wang; |
| 110 | Bounding Stratified Bernoulli Impulses for Ray Marching Gaussian Process Implicit Surfaces Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We introduce stratified Bernoulli impulses, enabling a fast point-level bound for individual realizations to replace unnecessary full noise evaluations. |
Junjie Chen; Zhimin Fan; Ling-Qi Yan; Junqiu Zhu; Yanwen Guo; Kun Zhou; Jie Guo; |
| 111 | Abstraction in Style: Beyond Texture and Color Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this work, we introduce Abstraction in Style (AiS), a generative framework that separates structural abstraction from visual stylization. |
Min Lu; Yuanfeng He; Anthony Chen; Jianhuang He; Pu Wang; Daniel Cohen-Or; Hui Huang; |
| 112 | GimmBO: Interactive Generative Image Model Merging Via Bayesian Optimization Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We propose GimmBO to support interactive exploration of adapter merging for image generation through Preferential Bayesian Optimization (PBO). |
Chenxi Liu; Selena Ling; Alec Jacobson; |
| 113 | Differentiable Neutron Transport Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Recent advances in differentiable rendering have demonstrated that inverse problems—such as recovering scene properties from observations—can be efficiently solved through gradient-based optimization, where the gradients are estimated through Monte Carlo methods.Inspired by these developments, we extend differentiable rendering techniques to neutron transport problems, enabling inverse design and sensitivity analysis in nuclear systems. To adapt these methods to the neutron transport problem, we generalize the automatic differentiation of Monte Carlo light transport simulation to multi-energy neutron transport; propose a new simplified way to handle moving geometric discontinuities; and propose new estimators for derivatives of volume integrals. |
Xi Deng; Maosen Tang; Michael Czekanski; David Bindel; Steve Marschner; |
| 114 | Deep Motion Warping Via Phase-Conditioned Diffusion Autoencoder Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: More recent learning-based editing approaches improve realism, but many of them encode motion into tightly entangled latent space, which makes them struggle to balance editing flexibility and content preservation. To address this, we propose a novel deep motion warping framework that explicitly disentangles the motion structure from global and stylistic attributes for intuitive motion editing. |
Bowen Zheng; Linjun Wu; Xinwei Jiang; Yujin Chai; Zijiao Zeng; He Wang; Xiaogang Jin; |
| 115 | MTPano: Multi-Task Panoramic Scene Understanding Via Label-Free Integration of Dense Prediction Priors Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Furthermore, the underlying relations between diverse dense prediction tasks in spherical spaces are underexplored. To address these challenges, we propose MTPano, a robust multi-task panoramic foundation model established by a label-free training pipeline. |
Jingdong Zhang; Xiaohang Zhan; Lingzhi Zhang; Yizhou Wang; Zhengming Yu; Jionghao Wang; Wenping Wang; Xin Li; |
| 116 | BrepForge: Factorized B-rep Synthesis Via Wireframe Composition and Boundary-Conditioned Surface Instantiation Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We observe a fundamental asymmetry in B-reps: while wireframe composition involves high-entropy structural decisions, the interior surface geometry is largely constrained by its boundary loops. Motivated by this observation, we propose BrepForge, a generative framework that factorizes B-rep synthesis into two stages: wireframe composition and boundary-conditioned surface instantiation. |
Jing Li; Yihang Fu; Falai Chen; |
| 117 | Autoregressive Modeling of Film with Applications in Video Montage Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Instead, at inference time, we introduce a footage-constrained decoding algorithm to select the best next shot from the input raw footage according to the statistical patterns learned from films. |
Marcelo Sandoval-Casta\~{n}eda; Fabian Caba Heilbron; Shiry Ginosar; Bryan Russell; Josef Sivic; Alexei Efros; Gregory Shakhnarovich; |
| 118 | See-through: Single-image Layer Decomposition for Anime Characters Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We introduce a framework that automates the transformation of static anime illustrations into manipulatable 2.5D models. |
Jian Lin; Chengze Li; Haoyun Qin; Kwun Wang Chan; Yanghua Jin; Hanyuan Liu; Chun Wang Choy; Xueting Liu; |
| 119 | MAViD: A Multimodal Framework for Audio-Visual Dialogue Understanding and Generation Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We propose MAViD, a novel Multimodal framework for Audio-Visual Dialogue understanding and generation. |
Youxin Pang; Jiajun Liu; Lingfeng Tan; Yong Zhang; Feng Gao; Xiang Deng; Zhuoliang Kang; Xiaoming Wei; Yebin Liu; |
| 120 | Heterogeneous Subspace Corrections for GPU Deformable Multibody Dynamics Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: While Newton-Krylov methods are popular for their matrix-free nature and good GPU compatibility, they often suffer from severe ill-conditioning and slow convergence when handling stiff contacts and material disparities in deformable multibody systems. In this paper, we present Heterogeneous Subspace Corrections (HSC), a novel Newton-CG variant to efficiently simulate such complex systems. |
Dewen Guo; Zhendong Wang; Minchen Li; Sheng Li; Guoping Wang; Huamin Wang; Chenfanfu Jiang; Yin Yang; |
| 121 | JGS2-GQ: Training-free 2nd Jacobi with Gaussian Quadrature Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: This paper proposes a training-free subspace integration algorithm based on classic Gaussian quadrature (GQ). |
Dewen Guo; Zixuan Lu; Zhiyong He; Yuqi Meng; Bohan Wang; Lei Lan; Weiwei Xu; Chenfanfu Jiang; Yin Yang; |
| 122 | PureSample: Neural Materials Learned By Sampling Microgeometry Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We present PureSample: a novel neural BRDF representation that allows learning a material’s appearance purely by sampling forward random walks on the microgeometry, which is usually straightforward to implement. |
Zixuan Li; Zixiong Wang; Jian Yang; Milo\v{s} Ha\v{s}an; Beibei Wang; |
| 123 | InvSculpt: Inverse Sculpting Modeling Via Controlled 3D Generation and A Vector Displacement Field Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We present InvSculpt, a novel inverse sculpting framework that decomposes a sculpted mesh into a high-fidelity underlying shape and reusable geometric details represented as a vector displacement field (VDF). |
Hengyu Meng; Lanjiong Li; Zhijing Shao; Yingda Yin; Lingting Zhu; Zeyu Hu; Xin Wang; Ligang Liu; Zeyu Wang; |
| 124 | SimArt: Decomposing Monolithic Meshes Into Sim-ready Articulated Assets Via MLLM Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: However dense voxel-based 3D tokenization yields long 3D token sequences and high memory overhead, limiting scalability to complex articulated objects. To address this, we propose SimArt, a unified MLLM framework that performs part-level decomposition and kinematic prediction jointly. |
Chuanrui Zhang; Minghan Qin; Yuang Wang; Baifeng Xie; Hang Li; Ziwei Wang; |
| 125 | Ref-DGS: Reflective Dual Gaussian Splatting Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Existing Gaussian splatting methods either fail to model near-field specular reflections or rely on explicit ray tracing at substantial computational cost. We present Ref-DGS, a reflective dual Gaussian splatting framework that addresses this trade-off by decoupling surface reconstruction from specular reflection within an efficient rasterization-based pipeline. |
Ningjing Fan; Yiqun Wang; Dong-Ming Yan; Peter Wonka; |
| 126 | A LoD of Gaussians: Out-of-Core Training and Rendering for Seamless Ultra-Large Scene Reconstruction Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We introduce A LoD of Gaussians, a framework for training and rendering ultra-large-scale Gaussian scenes on a single consumer-grade GPU without partitioning. |
Felix Windisch; Thomas K\{o}hler; Lukas Radl; Mattia D’urso; Michael Steiner; Dieter Schmalstieg; Markus Steinberger; |
| 127 | HairGPT: Strand-as-Language Autoregressive Modeling for Realistic 3D Hairstyle Synthesis Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Many existing generative approaches rely primarily on continuous diffusion fields, which entangle global topology with local texture and obscure the semantic and structural organization of hairstyles. To address this, we propose HairGPT, a strand-centric framework that treats strands as generative primitives and formulates realistic 3D hairstyle synthesis as a dual-decoupled autoregressive sequence modeling problem. |
Haimin Luo; Min Ouyang; Lan Xu; Jingyi Yu; |
| 128 | SHARP-GS: Scalable High-fidelity Accelerated Rendering Pipeline for Ultra-high Resolution 3D Gaussian Splatting Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We present SHARP-GS, a high-performance framework that unlocks real-time 8K rendering for immersive virtual experiences by overcoming the scaling bottlenecks of 3D Gaussian Splatting (3DGS). |
JunRan Ding; WeiHang Liu; YuKe Li; YiZhou Wang; AnTong Li; QiHan Ding; Xin Lou; JingYi Yu; |
| 129 | Learning A Delighting Prior for Facial Appearance Capture in The Wild Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: To bridge this gap, we propose to shift the paradigm into training a powerful delighting network as a prior to constrain the optimization. We leverage the OLAT dataset and the rendered Light Stage scans for training, and propose Dataset Latent Modulation (DLM) to seamlessly integrate these heterogeneous data sources. |
Yuxuan Han; Xin Ming; Tianxiao Li; Zhuofan Shen; Qixuan Zhang; Lan Xu; Feng Xu; |
| 130 | FreeOrbit4D: Training-Free Arbitrary Camera Redirection for Monocular Videos Via Foreground-Complete 4D Reconstruction Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: While recent diffusion-based methods achieve impressive visual generation quality, they often break down under large-angle viewpoint changes far from the original trajectory, where missing visual grounding leads to severe geometric ambiguity and temporal inconsistency. To address this, we present FreeOrbit4D, an effective training-free framework that tackles this geometric ambiguity by recovering a foreground-complete 4D proxy as structural grounding for video generation. |
Wei Cao; Hao Zhang; Fengrui Tian; Yulun Wu; Yingying Li; Shenlong Wang; Ning Yu; Yaoyao Liu; |
| 131 | Topologically Consistent Multi-view 3D Head Reconstruction Via Coarse-Guided Layered Surface Sampling Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We present SHELLS (Semantic Head Estimation via Layered Local Sampling), an efficient feed-forward framework for 3D head reconstruction in dense semantic correspondence from multi-view images. |
Timo Bolkart; Daoye Wang; Prashanth Chandran; |
| 132 | Global Discrete Optimization for Quad-Dominant Mesh Reduction Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We present a global, discrete optimization framework for quad-dominant mesh reduction that formulates simplification as an edge selection problem under coupled topological and geometric constraints. |
Yuzhe Luo; Jingchen Gao; Zherong Pan; Kui Wu; Xuebo Ji; Xiaogang Jin; Xifeng Gao; |
| 133 | Kinematic Kitbashing Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We introduce Kinematic Kitbashing, an optimization framework that synthesizes articulated 3D objects by assembling reusable parts conditioned on an abstract kinematic graph. |
Minghao Guo; Victor Zordan; Sheldon Andrews; Wojciech Matusik; Maneesh Agrawala; Hsueh-Ti Derek Liu; |
| 134 | Distributed Affine Body Dynamics with Adaptive Consensus Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We propose a distributed formulation of ABD using a consensus-based ADMM scheme. |
Jiafeng Liu; Wenhui Zhou; Xinming Pei; Yifan Peng; Huamin Wang; Yin Yang; Lei Lan; Weiwei Xu; |
| 135 | ComboStoc: Combinatorial Stochasticity for Diffusion Generative Models Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this paper, we study an under-explored but important factor of diffusion generative models, i.e., the combinatorial complexity. |
Rui Xu; Jiepeng Wang; Hao Pan; Yang Liu; Xin Tong; Shiqing Xin; Changhe Tu; Taku Komura; Wenping Wang; |
| 136 | Fast VEM Fluid Simulation Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We present FastVEM, an efficient boundary-conforming fluid simulation framework that enables high-fidelity flow-boundary interaction at substantially reduced cost. |
Runze Zhang; Bo Ren; |
| 137 | Manifold K-NN: Accelerated K-NN Queries for Manifold Point Clouds Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Our approach is founded on the geometric observation that if pi is the nearest neighbor of a query q in P, then the second nearest neighbor of q must reside either within the prefix set P1:i-1 = [p1, …, pi-1} or within pi’s successor list. By recursively extending this principle, we introduce Manifold k-NN, a recursive algorithmic scheme that significantly outperforms conventional kd-trees for manifold-aligned data. |
Pengfei Wang; Qinghao Guo; Haisen Zhao; Shiqing Xin; Shuangmin Chen; Changhe Tu; Wenping Wang; |
| 138 | Structural MAT: Clean and Scalable Medial Axis Simplification Via Explicit Surface Correspondence Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Our key insight is to explicitly track the correspondence between MAT vertices and surface regions throughout the progressive simplification process, ensuring that the resulting MAT triangles accurately reflect the intrinsic symmetries between surface patches. |
Pengfei Wang; Shuangmin Chen; Dongming Yan; Ying He; Shiqing Xin; Changhe Tu; Wenping Wang; |
| 139 | Multi-feature Radiance Baking Neural Networks for Instant Volumetric Rendering Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this paper, we present Multi-feature Radiance Baking Neural Networks (MRBNN), a neural volumetric rendering method that achieves real-time performance by leveraging analytic decomposition of scattering with an efficient learned representation. |
Jiaming Liang; Hongliang Yuan; Meng Gai; Guoping Wang; Sheng Li; |
| 140 | PR-Cage: Progressive Feasibility Relaxation for Tight Bounding Cage Generation Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this paper, we propose PR-Cage, a nested optimization framework for automated cage generation.For the outer control layer, we introduce a thickness parameter τ that defines a feasibility region; the evolving cage is guided by the τ-offset surface. |
Huibiao Wen; Kaikai Qin; Xinxin Su; Jingcheng Mei; Shuangmin Chen; Chongyang Deng; Changhe Tu; Shiqing Xin; Wenping Wang; |
| 141 | StyleID: A Perception-Aware Dataset and Metric for Stylization-Agnostic Facial Identity Recognition Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: This reveals the lack of a style-agnostic framework to evaluate and supervise identity consistency across varying styles and strengths. To address this gap, we introduce StyleID, a human perception-aware dataset and evaluation framework for facial identity under stylization. |
Kwan Yun; Changmin Lee; AYeong Jeong; Youngseo Kim; Seungmi Lee; Junyong Noh; |
| 142 | LagrangianSplats: Divergence-Free Transport of Gaussian Primitives for Fluid Reconstruction Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We introduce a reconstruction framework that structurally enforces both constraints. |
Ningxiao Tao; Baoquan Chen; Mengyu Chu; |
| 143 | ArtiFixer: Enhancing and Extending 3D Reconstruction with Auto-Regressive Diffusion Models Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: To solve these, we propose a two-stage pipeline that leverages two key insights. |
Riccardo De Lutio; Tobias Fischer; Yen-Yu Chang; Yuxuan Zhang; Zhangjie Wu; Xuanchi Ren; Tianchang Shen; Katar\'{\i}na T\'{o}thov\'{a}; Zan Gojcic; Haithem Turki; |
| 144 | Lucky High Dynamic Range Smartphone Imaging Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: This paper proposes an approach that robustly captures dynamic range using a handheld smartphone camera and lightweight networks suitable for running on mobile devices. |
Baiang Li; Ruyu Yan; Ethan Tseng; Zhoutong Zhang; Adam Finkelstein; Jiawen Chen; Felix Heide; |
| 145 | CaRaFe: Camera-Radar Radiance Fields for Scene Reconstruction Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We propose CaRaFe, a method that leverages the complementary strengths of camera and radar for 3D reconstruction in challenging urban settings. |
David Borts; Julian Ost; Shamik Basu; Tim Broedermann; Andrea Ramazzina; Christos Sakaridis; Mario Bijelic; Felix Heide; |
| 146 | GPU-accelerated Certified Hausdorff Distance Between Triangle Meshes Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We present a GPU-accelerated certified B&B algorithm that explicitly maintains enclosing lower and upper bounds on the directed Hausdorff distance and terminates once their normalized gap, measured with respect to the bounding-box diagonal of the source mesh, meets a user-prescribed tolerance. |
Haopeng Fan; Min Tang; Leonardo Sacht; Qiang Zou; Ruofeng Tong; Peng Du; |
| 147 | CoherentRaster: Efficient 3D Gaussian Splatting for Light Field Displays Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this paper, we propose CoherentRaster, a 3DGS-based light field rendering framework that performs subpixel-level rasterization. |
Gyujin Sim; Seungjoo Shin; Hosung Jeon; Gwangsoon Lee; Hyon-Gon Choo; Sunghyun Cho; |
| 148 | HL-OutPaint: Coarse-to-Fine Video Outpainting for High-Resolution Long-Range Videos Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this paper, we propose HL-OutPaint, a high-resolution video outpainting framework for long sequences. |
Jeongeun Park; Janghyeok Han; Geonung Kim; Hyun-Seung Lee; Kyuha Choi; Youngseok Han; Sunghyun Cho; |
| 149 | HairLRM: Strand-based Hair Modeling Via Large Reconstruction Models Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Using the LRM mesh as a structural anchor, we employ a novel Dual Orientation AutoEncoder to lift coarse geometry into high-fidelity strands. |
Yuefan Shen; Yican Dong; Xiufeng Huang; Zhongtian Zheng; Youyi Zheng; Kui Wu; |
| 150 | 8DNA: 8D Neural Asset Light Transport By Distribution Learning Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: High-fidelity 3D assets exhibit intriguing global illumination effects like subsurface scattering, glossy interreflections, and fine-scale fiber scatterings, which often involve long scattering paths that are expensive to simulate. We introduce 8D neural assets (8DNA) to pre-bake these light transport effects into neural representations. |
Liwen Wu; Haolin Lu; Bing Xu; Milo\v{s} Ha\v{s}an; Ravi Ramamoorthi; |
| 151 | A Real-time, Multiscale and Procedural Feather Appearance Model Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We propose a complete pipeline for modeling and rendering realistic bird feathers from a single photograph, achieving both high visual fidelity and practical efficiency. |
Xiang Chen; Bin Chen; Shouyi Wang; Zahra Montazeri; Lingqi Yan; Lu Wang; Junqiu Zhu; |
| 152 | Surface Power Diagrams for Knit Singularity Placement Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We present an algorithm for global knit structure planning that leverages a generalization of power diagrams to triangulated surfaces. |
Rahul Mitra; Matt\'{e}o Couplet; Ruichen Liu; Jonathan Ng; Ruza Markov; William Batara Jeremiah Samosir; Megan Hofmann; Edward Chien; |
| 153 | Volume-Preserving LBM-MPM Coupling for Air-Water-Sand Mixtures Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We present a novel, physically-based simulation framework for sand-water-air mixtures that couples a Lattice Boltzmann Method (LBM) for weakly-compressible two-phase fluids with a Material Point Method (MPM) for granular sand. |
Xiaoyu Xiao; Haoxiang Wang; Xiaokang Yang; Mathieu Desbrun; Wei Li; |
| 154 | DiffSurFlow: Efficient and Robust Differentiable Fluid Optimization Via Surrogate Strategy on Flow Map Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: This paper presents a highly efficient and robust differentiable flu::id framework, centered on a novel surrogate gradient method that utilizes the flow map structural advantages. |
Yuhao Quan; Hui Wang; Weile Lian; Zhi Wang; Xubo Yang; |
| 155 | Gradient Domain Reconstruction for Monte Carlo PDE Solvers Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Inspired by gradient-domain rendering, we introduce a gradient-domain framework for Poisson problems. |
Jiaqi Wu; Xuejun Hu; Shuang Zhao; Kun Xu; |
| 156 | DPF: Differentiable Polyphase Filtering for Large-Kernel Approximation Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this paper, we propose a novel framework based on Polyphase Filtering, which enables the differentiable optimization of sparse kernels across varying resolutions. |
Zhe Cao; Zhizhen Wu; Zhonggui Chen; Rui Wang; Yuchi Huo; |
| 157 | Adaptive Ray Marching for Rendering Gaussian Process Implicit Surfaces Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Despite this generality, computing GPIS–ray intersections requires sampling conditional multivariate Gaussian distributions along each ray and remains prohibitively expensive. We introduce an online sampling algorithm that draws these distributions incrementally, and an adaptive marching scheme that takes large steps where the surface is provably absent, minimizing the probability of missed intersections. |
Zhiqian Zhou; Dario Seyb; Shuang Zhao; |
| 158 | Efficient Multiscale Lanczos Eigenpair Extraction Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this paper we present a simple multigrid extension to accelerate the convergence and robustness of the implicitly restarted Lanczos method, and we demonstrate the efficiency of our method on a variety of problems commonly found in geometry processing and graphics. |
Theo Braune; J\'{e}r\'{e}mie Dumas; Jean-Marc Thiery; |
| 159 | MorphSkein: A Shape-Changing Afterimage Display Preserving Pixel Density During Surface-Area Changes Across Troposkein-Based Shapes Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We introduce MorphSkein, a shape-changing after-image display that preserves initial density (1.44 px/cm2) across naturally occurring axisymmetric shapes generated by spinning cables (troposkeins). |
Maxime Daniel; Shariff AM Faleel; Pourang Irani; |
| 160 | Reality Check: How Avatar and Face Representation Affect The Perceptual Evaluation of Synthesized Gestures Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Prior work suggests these visual choices can bias motion judgments, but controlled evidence remains limited. We address this gap with controlled evaluations of co-speech gestures across motion sources, spanning seven representative avatar renderings used in contemporary research and application pipelines. |
Haoyang Du; Yinghan Xu; John Dingliana; Brian Keegan; Rachel McDonnell; Cathy Ennis; |
| 161 | Mix3R: Mixing Feed-forward Reconstruction and Generative 3D Priors for Joint Multi-view Aligned 3D Reconstruction and Pose Estimation Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We present Mix3R, a novel generative 3D reconstruction method which mixes feed-forward reconstruction and 3D generation into a single framework in an aligned manner. |
Siyou Lin; Zhou Xue; Hongwen Zhang; Liang An; Dongping Li; Shaohui Jiao; Yebin Liu; |
| 162 | Pixel Cube: Diffusion-based Portrait Video Relighting Through Realistic Lighting Reproduction Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We present a diffusion-based method for relighting dynamic portrait videos with photorealism and temporal consistency. |
Yufan Zhang; Yu Ji; Ayo Ajiboye; Rundi Wu; Yu Guo; Changxi Zheng; Jinwei Ye; |
| 163 | Generic Variational Spacetime Optimization of Vortex Core Manifolds Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We introduce a generic variational framework for the computation of optimal vortex cores in 3D unsteady flow that combines a geometric vortex core model with explicit reference frame optimization. |
Xingdi Zhang; Peter Rautek; Markus Hadwiger; |
| 164 | PixTex: Consistent 3D Texturing Via Pixel-Space Multi-View Diffusion Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Existing texture generation methods rely heavily on latent diffusion models, whose VAE-based spatial compression inherently limits fine-grained detail preservation and degrades pixel-level multi-view consistency. To address this limitation, we introduce PixTex, the first pixel-space multi-view diffusion framework for texture generation, which achieves substantially improved multi-view consistency. |
Yuqing Zhang; Yan-Pei Cao; Hao Xu; Yiqian Wu; Sirui Lin; Yuqing Wang; Ding Liang; Yuan-Chen Guo; Xiaogang Jin; |
| 165 | FIT: A Large-Scale Dataset for Fit-Aware Virtual Try-On Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: (3) We introduce person identity preservation into our re-texturing model to generate paired person images (same person, different garments) for supervised training. |
Yuanhao Wang; Johanna Karras; Yingwei Li; Ira Kemelmacher-Shlizerman; |
| 166 | ATGS: Anchored Temporal Gaussian Splatting for Long Volumetric Video Representation Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Volumetric video enables immersive free viewpoint rendering of dynamic real world scenes, yet existing methods struggle with long sequences and complex motions, often leading to temporal instability and visual artifacts. To address these challenges, we propose ATGS, a Gaussian splatting based framework for volumetric video reconstruction. |
Jiahao Wu; Jie Liang; Die Hu; Jiayu Yang; Kaiqiang Xiong; Xiang Li; Xiaoyun Zheng; Chao Wang; Ronggang Wang; |
| 167 | Generative Modeling with Orbit-Space Particle Flow Matching Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We present Orbit-Space Geometric Probability Paths (OGPP), a particle-native flow-matching framework for generative modeling of particle systems. |
Sinan Wang; Jinjin He; Shenyifan Lu; Ruicheng Wang; Greg Turk; Bo Zhu; |
| 168 | Soft Anisotropic Diagrams for Differentiable Image Representation Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We introduce Soft Anisotropic Diagrams (SAD), an explicit and differentiable image representation parameterized by a set of adaptive sites in the image plane. |
Laki Iinbor; Zhiyang Dou; Wojciech Matusik; |
| 169 | EgoRelight: Egocentric Human Capture and Illumination Recovery for Relightable and Photoreal Avatar Rendering Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this paper, we present EgoRelight, a holistic framework for egocentric telepresence that simultaneously captures full-body human performance, synthesizes photorealistic and relightable appearance, and estimates high dynamic range (HDR) environment maps from a single HMD. |
Jianchun Chen; Yinda Zhang; Rohit Pandey; Thabo Beeler; Marc Habermann; Christian Theobalt; |
| 170 | Img2CADSeq: Image-to-CAD Generation Via Sequence-Based Diffusion Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Boundary Representation (BRep) is the standard format for Computer-Aided Design (CAD), yet reconstructing high-quality BReps from single-view images remains challenging due to the complexity of topological constraints and operation sequences. We present Img2CADSeq, a multi-stage pipeline that overcomes these limitations by encoding CAD sequences into a three-level hierarchical codebook. |
Shiyu Tan; Zixuan Zhao; Hao Gao; Zhiheng Chen; Xiaolong Yin; Enya Shen; |
| 171 | GeoQuery: Geometry-Query Diffusion for Sparse-View Reconstruction Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We observe that this mechanism often fails when the rendered novel views output by 3DGS are heavily corrupted: damaged query features lead to erroneous cross-view retrieval, resulting in inconsistent rendering refinement. To address this, we propose GeoQuery, a geometry-guided diffusion framework that integrates generative priors with explicit geometric cues via a novel Geometry-guided Cross-view Attention (GCA) mechanism. |
Xiao Cao; Yuze Li; Youmin Zhang; Jiayu Song; Cheng Yan; Wen Li; Lixin Duan; |
| 172 | An Extended Full GKS Formulation for High-Efficiency and Low-Memory Two-Phase Flow Simulation Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this paper, we propose a novel two-phase flow solver that achieves this objective. |
Yiheng Wu; Kai Bai; Xiaopei Liu; |
| 173 | UniVidX: A Unified Multimodal Framework for Versatile Video Generation Via Diffusion Priors Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this paper, we present UniVidX, a unified multimodal framework designed to leverage VDM priors to enable versatile video generation. |
Houyuan Chen; Hong Li; Xianghao Kong; Tianrui Zhu; Shaocong Xu; Weiqing Xiao; Yuwei Guo; Chongjie Ye; Lvmin Zhang; Hao Zhao; Anyi Rao; |
| 174 | A Unified Homogenization Framework for Straight- and Curved-Crease Origami Materials Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We present a computational framework for numerical homogenization of origami materials—thin sheets structured with periodic crease patterns that, once folded, exhibit diverse and often unusual mechanical properties. |
Mingjie Li; Juan Montes Maestre; Emilien Ganier; Klara Mundilova; Mark Pauly; Bernhard Thomaszewski; |
| 175 | Graphical X Splatting (GraphiXS): A Graphical Model for 4D Gaussian Splatting Under Uncertainty Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We propose a new framework to systematically incorporate data uncertainty in Gaussian Splatting. |
Do\u{g}a Y\i{}lmaz; Jialin Zhu; Deshan Gong; He Wang; |
| 176 | GCDT: A Highly Parallel GPU Algorithm for Large-Scale Constrained Delaunay Triangulation Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We present a highly parallel GPU-based method capable of computing CDTs on inputs with millions of vertices, while efficiently and robustly enforcing arbitrary valid constraints. |
Peng Fan; Min Tang; Ruofeng Tong; Lili He; Peng Du; Hailong Li; |
| 177 | TwinPose: Person-Specific Subspaces for Multi-View 3D Pose Estimation Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: However, despite strong progress, recent state-of-the-art methods still face critical limitations: 1) They often depend on global optimization over a large and complex set of multi-view 2D joints to jointly infer 3D poses for all individuals, making the process highly complex and prone to suboptimal solutions; 2) Their tight coupling with the bottom-up detector OpenPose hinders the use of more advanced top-down or single-stage 2D pose estimators and restricts the integration of richer instance-level cues learned by these models. To address these limitations, we propose TwinPose, a novel framework that alleviates the complexity of global pose inference by optimizing within person-specific 3D pose subspaces, while fully supporting diverse 2D pose detectors and effectively leveraging pose-instance cues. |
Wenwu Yang; Tianyi He; Jiwei Ding; Xun Wang; Rong Zhang; Kun Zhou; |
| 178 | Controllable Texture Tiling Via Diffusion Transformers with Transformed Rotary Embeddings Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this paper, we propose a novel framework for controllable and high-fidelity texture tiling based on Diffusion Transformers. |
Junrong Huang; Zhiyuan Zhang; Rui Tang; Hongbo Fu; Jing Liao; |
| 179 | MUSIC: Learning Muscle-Driven Dexterous Hand Control Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We present a data-driven approach for physics-based, muscle-driven dexterous control that enables musculoskeletal hands to perform precise piano playing for novel pieces of music outside the reference dataset. |
Pei Xu; Yufei Ye; Shuchu Sun; Yu Ding; Elizabeth Schumann; C. Karen Liu; |
| 180 | VfxDB: A Visual Effects Volume Dataset and Benchmark for VDB-Native Generative Modeling Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this paper, we introduce a 1-million-sample VFX sequence of VDB dataset with standardized preprocessing, consistent metadata, and protocol-ready splits, together with a reproducible benchmark suite for both static volume generation and sequence volumes generation. |
Junwei Shu; Hantang Liu; Dawei Miao; Wenzheng Song; Mingyang Yuan; Wenjie Liu; Changgu Chen; Yang Li; Changbo Wang; |
| 181 | Efficient B-Spline Finite Elements for Cloth Simulation Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We present an efficient B-spline finite element method (FEM) for cloth simulation. |
Yuqi Meng; Yihao Shi; Kemeng Huang; Zixuan Lu; Ning Guo; Taku Komura; Yin Yang; Minchen Li; |
| 182 | Untangling Surfaces Via Shape and Mesh Repulsion Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We introduce an energy-based framework that enforces surface embeddedness simultaneously at the shape and mesh levels, based on the insight that successful untangling requires accounting for both global shape-level interactions and local mesh-level interactions. |
Ji\v{r}\'{\i} Minar\v{c}\'{\i}k; Michael Liu; Keenan Crane; Minchen Li; |
| 183 | Differentiable Voxelization of Surface Representations Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Optimizing a surface representation based on a volumetric properties by gradient descent requires the derivatives of the volume relative to its bounding surface. We derive this gradient for winding numbers and show that it can be efficiently computed for volumetric values sampled on a regular grid (voxel representation) and surface parameters based on vertex sets (triangle meshes). |
Tobias Djuren; Ugo Finnendahl; Markus Worchel; Hendrik Meyer; Marc Alexa; |
| 184 | Low-Rank Koopman Deformables with Log-Linear Time Integration Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We present a low-rank Koopman operator formulation for accelerating deformable subspace simulation. |
Yue Chang; Peter Yichen Chen; Eitan Grinspun; Maurizio M. Chiaramonte; |
| 185 | LUCID: Learning Unified Control for Image Deflaring and Exposure Mastery in Nighttime Photography Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Conventional approaches address these factors in isolation, overlooking the fact that these degradations are fundamentally entangled. To bridge this gap, we introduce LUCID, a unified framework that reframes nighttime restoration as a continuous and controllable process rather than a fixed correction. |
Tingyu Yang; Yuan Cheng; Xiaoyun Yuan; |
| 186 | 4D Human-Scene Reconstruction from Low-Overlap Captures Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Video diffusion models have emerged as another option, but they show geometrically inconsistent results for humans. To address these limitations, we propose StudioRecon, a pipeline that reconstructs 4D human scenes from sparse, low-overlap cameras by decoupling background and humans. |
Minhyuk Hwang; Sangmin Kim; Seunguk Do; Daneul Kim; Jaesik Park; |
| 187 | Gradient-based Approximation of Nonuniform Low-Discrepancy Samples Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We introduce an optimization framework to approximate non-uniform low-discrepancy samples by numerically minimizing the discrepancy metric for non-uniform samples. |
Xiangyu Li; Ege Ciklabakkal; Daniel Ritchie; Toshiya Hachisuka; |
| 188 | DualBrep: A Dual-Field Continuous Representation for B-rep Modelling Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this work we introduce DualBrep, a novel continuous representation that unifies B-rep geometry and topology within a fully structured Euclidean domain. |
Yilin Liu; Pradeep Jayaraman; Chinthala Reddy; Xiang Xu; Hooman Shayani; |
| 189 | Better Bending: Analysis, Construction and Verification of Discrete Bending Models for Kirchhoff-Love Shells Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: While thin shells have ubiquitous applications and have been studied inside and outside computer graphics for decades, there is little consensus on how to best discretize them. We systematically study models for simulating bending of Kirchhoff-Love shells, with the goal of making practical recommendations, backed by careful numerical experiments, of when and how these models should be used. |
Zhen Chen; Danny Kaufman; Etienne Vouga; |
| 190 | AGIPC: Adaptive In-Solve Algebraic Coarsening for GPU IPC Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We present algebraic adaptive in-solve coarsening, a GPU-oriented method that dynamically reduces DoF within the Newton solve of implicit time integration without explicit topological modification. |
Xuan Wang; Zhaofeng Luo; Minchen Li; Taku Komura; Kemeng Huang; |
| 191 | Sample Matching for Joint Extinction Gradient Estimation in Differentiable Volume Rendering Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We observe that the extinction gradients split into two components on structurally different integration domains: a scattering term evaluated at a single path vertex, and a transmittance term integrated along the ray segment. |
Ruihan Yu; Yu-Chen Wang; Jingwang Ling; Feng Xu; Shuang Zhao; |
| 192 | The PhaseTree: Multiphase Signed Distance Fields Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We introduce the PhaseTree, a novel hierarchical construction-tree representation for compactly modeling volumetric objects composed of multiple phases or materials across scales. |
Eric Galin; Pierre Hubert-briere; Marie-Paule Cani; Adrien Peytavie; Eric Gu\'{e}rin; Hugo Schott; |
| 193 | Mat\'{e}rn Noise for Triangulation-Agnostic Flow Matching on Meshes Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We use it as our noise model, and adapt FM to the triangulation-agnostic setting by using a state-of-the-art approach for learning signals on meshes in the gradient domain—PoissonNet—as the denoiser. |
Tianshu Kuai; Arman Maesumi; Daniel Ritchie; Noam Aigerman; |
| 194 | Inverse Rendering for Discrete X-Ray Computed Tomography Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Discrete tomography has been extensively studied over the past five decades, resulting in a range of mature reconstruction algorithms.In this work, we introduce a new reconstruction method that draws inspiration from both classical computed tomography and recent advances in inverse rendering, demonstrating that a remarkably simple gradient-based inversion can significantly surpass the reconstruction quality of standard methods such as SIRT, DART, and TVR-DART. |
Lovro Nuic; Ziyi Zhang; Korbinian Sager; Wenzel Jakob; |
| 195 | Mixed Material Point Methods for Stiff Elastoplasticity Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We present a family of mixed Material Point Methods well suited for the CFL-rate simulation of stiff elastoviscoplastic materials, up to the incompressible limit. |
Gilles Daviet; |
| 196 | Physics-Inspired Procedural Texturing of Extremely Deformable Surfaces Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In the real world, the appearance of surface details on a deforming material changes through the interplay of physical processes such as rupturing, exposure of internal structure, or wrinkling. Motivated by these behaviors, in this work we explore how physical principles can guide the texturing methods based on the measure of surface deformation.We present two novel wave-based procedural texturing algorithms which reproduce common physical properties like advection and self-similarity, enabling the plausible animation of deforming objects with extreme texture map distortions. |
Aleksei Kalinov; Micka\{e}l Ly; Christian Hafner; Chris Wojtan; |
| 197 | EgoForce: Forearm-Guided Camera-Space 3D Hand Pose from A Monocular Egocentric Camera Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: As a result, models typically require extensive training on device-specific datasets, which are costly and laborious to acquire. This paper addresses these challenges by introducing EgoForce, a monocular 3D hand reconstruction framework that recovers robust, absolute 3D hand pose and its position from the user’s (camera-space) viewpoint. |
Christen Millerdurai; Shaoxiang Wang; Yaxu Xie; Vladislav Golyanik; Didier Stricker; Alain Pagani; |
| 198 | Neural Cellular Automata: From Cells to Pixels Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: This limitation stems from (1) training time and memory requirements that grow quadratically with grid size, (2) the strictly local propagation of information that impedes long-range cell communication, and (3) the heavy compute demands of real-time inference at high resolution. In this work, we overcome this limitation by pairing an NCA that evolves on a coarse grid with a lightweight implicit decoder that maps cell states and local coordinates to appearance attributes, enabling the same model to render outputs at arbitrary resolution. |
Ehsan Pajouheshgar; Yitao Xu; Ali Abbasi; Alexander Mordvintsev; Wenzel Jakob; Sabine S\{u}sstrunk; |
| 199 | Neural Particle Automata: Learning Self-Organizing Particle Dynamics Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We introduce Neural Particle Automata (NPA), a Lagrangian generalization of Neural Cellular Automata (NCA) from static lattices to dynamic particle systems. |
Ehsan Pajouheshgar; Hyunsoo Kim; Sabine S\{u}sstrunk; Wenzel Jakob; Jinah Park; |
| 200 | EAG-PT: Emission-Aware Gaussians and Path Tracing for Diffuse Indoor Scene Reconstruction and Editing Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We present Emission-Aware Gaussians and Path Tracing (EAG-PT), a method for physically based reconstruction and rendering of indoor scenes using a unified 2D Gaussian representation, targeting editable diffuse global illumination. |
Xijie Yang; Mulin Yu; Changjian Jiang; Kerui Ren; Tao Lu; Jiangmiao Pang; Dahua Lin; Bo Dai; Linning Xu; |
| 201 | BodyReLux: Temporally Consistent Full-Body Video Relighting Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We present BodyReLux, a subject-specific video diffusion-based framework for relighting full-body human performances in a temporally consistent way. |
Li Ma; Mingming He; Xueming Yu; David George; Ahmet Tasel; Paul Debevec; Julien Philip; |
| 202 | CameraSquad: Achieving Content Consistency in Parallel Multi-Trajectory Camera-Controlled Video Generation Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We propose CameraSquad, a multi-trajectory camera control framework that supports both single-trajectory and parallel multi-trajectory generation. |
Zhufeng Xu; Xuan Gao; Bailin Deng; Yikang Ding; Xiaoqiang Liu; Haoxian Zhang; Pengfei Wan; Hongbo Fu; Lin Gao; |
| 203 | MeshFlow: Mesh Generation with Equivariant Flow Matching Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Meshes are among the most common 3D scene representations, but directly generating meshes is challenging largely because the mesh representation contains many structures, such as permutation invariance of vertices or faces. To address this challenge, we present a novel approach that learns to generate triangle meshes represented as triangle soups. |
Qi Sun; Kiyohiro Nakayama; Jing Nathan Yan; Qixing Huang; Alexander Rush; Leonidas Guibas; Gordon Wetzstein; Jing Liao; Guandao Yang; |
| 204 | Floating-Point Robustness in Parametric Surface Continuous Collision Detection: From Algorithm to Benchmarking Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this paper, we present the first floating-point-robust CCD framework for parametric surfaces. |
Xuwen Chen; Junyu Wang; Cheng Yu; Xingyu Ni; Meng Zhang; Bin Wang; Mengyu Chu; Baoquan Chen; |
| 205 | Component Modes Synthesis Method with Multiple Partitions for Large-scale Eigenvalue Problem Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We demonstrate that a much more effective subspace can be constructed by combining substructure eigenmodes from multiple spatially staggered partitions of the input domain. |
Chongyao Zhao; Junzhou Yin; Hujun Bao; Jin Huang; |
| 206 | Mechanical Cloaking of Halftoned Imagery Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: For an external observer, this creates the surprising effect where the object appears mechanically isotropic and homogeneous while its porous structure resembles a target image. We introduce a parametric class of porous structures suitable for this problem, as demonstrated by numerical experiments. |
Jon\`{a}s Mart\'{\i}nez; Brisard S\'{e}bastien; Kostas Danas; Eric Garner; Siddhant Kumar; Sylvain Lefebvre; |
| 207 | Composing People Together: Iterative Pose-Image Generation for Multi-Person Interaction Scenes Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Despite recent progress, text-to-image models still struggle to generate semantically diverse and compositionally accurate multi-person interaction scenes, often collapsing to repetitive layouts, stereotypical poses, and poorly grounded interactions. In this work, we bridge this gap by introducing a dual pose–image representation that brings person-centric structural priors into pretrained diffusion transformers. |
Wenxuan Peng; Bharath Hariharan; Hadar Averbuch-Elor; |
| 208 | Raster2Seq: Polygon Sequence Generation for Floorplan Reconstruction Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: To this end, we propose Raster2Seq, framing floorplan reconstruction as a sequence-to-sequence task in which floorplan elements—such as rooms, windows, and doors—are represented as labeled polygon sequences that jointly encode geometry and semantics. |
Hao Phung; Hadar Averbuch-Elor; |
| 209 | Dichoptic Foveation Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this paper, we develop a psychophysical framework to measure the perception of natural image stimuli with interocular frequency differences across the visual field. |
Henry Kam; Colin Groth; Jenna Kang; Pratham Saraf; Qi Sun; Kenneth Chen; |
| 210 | Adapting Quality Metrics to Tone Mapping Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Tone mapping evaluation is difficult because of the substantial differences in absolute luminance between high dynamic range (HDR) reference and tone-mapped standard dynamic range (SDR) test content. To address this challenge, we collected a new tone mapping evaluation dataset, focused on fundamental tone mapping operations, and combined it with several existing tone mapping quality assessment datasets. |
Kenneth Chen; Dongyeon Kim; Yuta Asano; Alexandre Chapiro; Qi Sun; Rafa\l{} K. Mantiuk; |
| 211 | Probe-based Walk on Spheres for Efficient Path Reusing Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We introduce a new variance reduction framework based on reusing intermediate states along each random walk. |
Wanchao Huang; Yutian Zhu; Qing Fang; Ligang Liu; |
| 212 | Learning Laplacian Eigenspace with Mass-Aware Neural Operators on Point Clouds Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: The eigendecomposition of the Laplace–Beltrami Operator (LBO) is fundamental to geometric analysis, yet computing its low-frequency eigenmodes remains a significant bottleneck due to the high cost of iterative solvers on large-scale data. To amortize this cost, we introduce the Neural Eigenspace Operator (NEO), a feed-forward framework designed to predict the spectrum directly from point clouds. |
Zherui Yang; Tao Du; Ligang Liu; |
| 213 | FLASHand: Feed-forward ReLightable and Animatable Single-view Hand Reconstruction Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In contrast, existing single-view hand reconstruction methods typically struggle to disentangle global illumination, resulting in textures with baked-in shading artifacts. To address these challenges, we propose FLASHand, the first feed-forward relightable and animatable 3D hand reconstruction model from a single RGB image. |
Ling-Xiao Zhang; Lin Gao; Wei-Hong He; Yu-Xuan Yang; Yunbing Xing; Yu-Kun Lai; Yiqiang Chen; |
| 214 | A Generalizable Light Transport 3D Embedding for Global Illumination Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: While per-scene neural methods lack generalization and screen-space approaches inherently suffer from view inconsistency, prior 3D neural rendering methods face a severe scalability barrier, restricting them to small, object-centric meshes. To overcome these trade-offs, we introduce a generalizable light transport 3D embedding that predicts global illumination directly from 3D scene configurations without rasterized or path-traced illumination cues, per-scene retraining or screen-space limitations. |
Bing Xu; Mukund Varma T; Cheng Wang; Tzu-mao Li; Lifan Wu; Bartlomiej Wronski; Ravi Ramamoorthi; Marco Salvi; |
| 215 | Points As Tori: Fast Pointwise Signed Distance for Point Clouds Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We describe a method for computing signed distance to point clouds that allows fast pointwise evaluation at arbitrary spatial resolution. |
Nicole Feng; Ioannis Gkioulekas; Keenan Crane; |
| 216 | Subgrid Marching Tetrahedra Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We describe a method for recovering a manifold, intersection-free triangle mesh from the points where edges of a tetrahedral grid pierce a continuous surface. |
Hossein Baktash; Mark Gillespie; Keenan Crane; |
| 217 | Robust Planar Maps for 3D Vectorization Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: This paper describes a strategy for vectorizing 3D scenes with proper occlusion. |
Robert Fuchs; Keenan Crane; |
| 218 | VideoNeuMat: Neural Material Extraction from Generative Video Models Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We present VideoNeuMat, a two-stage pipeline that extracts reusable neural material assets from video diffusion models. |
Bowen Xue; Saeed Hadadan; Zheng Zeng; Fabrice Rousselle; Zahra Montazeri; Milo\v{s} Ha\v{s}an; |
| 219 | Scalable GPU Construction of 3D Voronoi and Power Diagrams Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this paper, we present a highly parallelizable GPU algorithm for the fast construction of large-scale 3D Voronoi and power diagrams. |
Bernardo Taveira; Carl Lindstr\{o}m; Maryam Fatemi; Lars Hammarstrand; Fredrik Kahl; |
| 220 | Dual Contouring Over Expanded Cubes (DCx) for Zero-Level Set Extraction from Neural Unsigned Distance Functions Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We present DCx, an extension of the standard Dual Contouring (DC) method which was originally proposed for isosurface extraction from signed distance functions (SDFs). |
Qingchao Bao; Xuhui Chen; Jingpeng Yin; Fei Hou; Wencheng Wang; Hong Qin; Ying He; |
| 221 | SharpNet: Enhancing MLPs to Represent Functions with Controlled Non-differentiability Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We present SharpNet, a modified MLP architecture that encodes user-specified sharp features by augmenting the network with an auxiliary feature function defined as the solution to Poisson’s equation with jump Neumann boundary conditions. |
Hanting Niu; Junkai Deng; Fei Hou; Wencheng Wang; Ying He; |
| 222 | MegaNorm: Local Patch Embeddings for Efficient and Robust Point Normal Orientation at Super-Large Scale Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this paper, we propose a robust and efficient approach for orienting normals on super-large, non-watertight scenes. |
Zhuodong Li; Zengke Liu; Fei Hou; Xuhui Chen; Wencheng Wang; Ying He; |
| 223 | HumanFlow: Controllable Human Image Generation Via Flow Matching Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We present HumanFlow, a unified flow-matching-based framework that enables high-fidelity and controllable full-body human image generation under diverse human-centric control conditions. |
Wenzhuo Fan; Hongsheng Zheng; Jianchi Sun; Fei Fang; Hong Ding; Chunxia Xiao; |
| 224 | Tempo3D: Efficient Temporal-Aware Fine-Tuning and Multi-View Latent Aggregation for 3D Generation Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this work, we propose Tempo3D, a resource-efficient paradigm for high-fidelity VecSet-based 3D generation via efficient temporal-aware fine-tuning and multi-view latent aggregation. |
Huizhi Zhu; Jiongming Qin; Yusen Wang; Chunxia Xiao; |
| 225 | Kinetic Predicted-Moment Flux Reconstruction for High-Order High-Performance Fluid Simulation Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We present Kinetic Predicted-Moment Flux Reconstruction (KPM-FR), a high-order kinetic-based scheme for low-Mach-number weakly compressible flows that advances all three fronts within a single framework. |
Zike Xu; Xuan Zhang; Xiaopei Liu; |
| 226 | Relit-LiVE: Relight Video By Jointly Learning Environment Video Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this work, we present Relit-LiVE , a novel video relighting framework that produces physically consistent, temporally stable results without requiring prior knowledge of camera pose. |
Weiqing Xiao; Hong Li; Xiuyu Yang; Houyuan Chen; Wenyi Li; Tianqi Liu; Shaocong Xu; Chongjie Ye; Hao Zhao; Beibei Wang; |
| 227 | Gabor Fields: Orientation-Selective Level-of-Detail for Volume Rendering Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Additionally, such solutions do not guarantee a smooth transition between different hierarchy levels. To address these limitations, we propose Gabor Fields, a mixture of Gabor kernels that enables continuous, orientation-selective frequency filtering at no cost. |
Jorge Condor; Nicolai Hermann; Mehmet Ata Yurtsever; Piotr Didyk; |
| 228 | DeepMill++: Neural Guidance Meets Rasterization for Efficient Accessibility Analysis Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this paper, we introduce DeepMill++, a conservative and highly efficient framework for cutter accessibility analysis on arbitrary triangular meshes. |
Fanchao Zhong; Yao Zhang; Guanze Xin; Peng-Shuai Wang; Lin Lu; Changhe Tu; Haisen Zhao; |
| 229 | Real-Time Light-Field Path Tracing for 3D Displays Via Sparse Spatial-Angular-Temporal Reconstruction Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We introduce a unified algebraic framework governed by three mathematical primitives that respectively decouple rendering logic from heterogeneous optical hardware, establish deterministic geometric connectivity across disparate viewpoints, and enable atomic access to unstructured sparse data. |
Zongyuan Yang; Liulei Zou; Ling Zhu; Yongping Xiong; Honghui Fan; Baolin Liu; Yingde Song; Yu Zhu; Chang Zeng; Wangping Ye; |
| 230 | Role-Aware Virtual Agents for Navigational Interaction Guided By A Multimodal Large Language Model Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We present a role-aware virtual agent navigational interaction that generates consistent, role-aligned movement behaviors. |
Minyoung Kim; Changyang Li; Cuong Nguyen; Lap-Fai Yu; |
| 231 | CAdam: Context-Adaptive Moment Estimation for 3D Gaussian Densification in Generative Distillation Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We diagnose this failure as a Densification Dilemma stemming from the stochastic nature of generative guidance: the standard magnitude-based accumulation indiscriminately aggregates transient noise alongside geometric signals, making it difficult to strike a balance between over-densification and under-fitting. To resolve this, we introduce Context-Adaptive Moment Estimation (CAdam), a novel framework that reinterprets densification as a statistically grounded signal verification problem. |
SeungJeh Chung; Geonho Park; Misong Kim; HyeongYeop Kang; |
| 232 | GauSmoke: Hybrid Physics-Optical Gaussian Splatting for Sparse Smoke Reconstruction Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Current dynamic deformation-based 3D Gaussian Splatting (3DGS) methods use heuristic image-space warps, which often overfit limited observations via non-physical primitive scaling or drifting, producing floaters and geometric distortions. To address these challenges, we propose a hybrid, physics-aware fluid representation that injects physical constraints directly into the 3DGS pipeline. |
Wenran Zhang; Yuxiang Cai; Letian Huang; Dongwei Ye; Jie Guo; Bo Ren; |
| 233 | Generalized Spherical Harmonics Products Using Spherical Grids Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Existing SH product methods face two key challenges: insufficient computational efficiency, and the inflexible requirement that all input functions share the same SH order. To overcome these limitations, we introduce the Generalized Spherical Harmonics Product, a novel formulation that supports inputs with different SH orders and allows flexible truncation of the output.We further propose an efficient and practical computation approach based on Spherical Grids (SphGrid). |
Di An; Jiaqi Wu; Bowen Xu; Lingqi Yan; Kun Xu; |
| 234 | Spatio-Temporal Control Variates with ReSTIR for Real-Time Rendering Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: This inevitably leads to color noise in scenes with complex chromatic lighting or materials. In this work, we present Reservoir-based Spatio-Temporal Control Variates (ReSTCV), a novel framework that addresses this problem by integrating Spatio-Temporal Control Variates (STCV) into ReSTIR. |
Zhong Shi; Cunhao Wu; Lifan Wu; Kun Xu; |
| 235 | Successive Height Preintegration for A Height-Interdependent Path Formulation of Multiple Bounces in Smith Microfacet BRDFs Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this paper, we propose a novel derivation of multiple-bounce Smith microfacet bidirectional reflectance distribution functions (BRDFs) based on a partial adoption of the independent-bounce assumption. |
Siyuan Zhang; Takuya Funatomi; Yuki Fujimura; Yasuhiro Mukaigawa; Hiroyuki Kubo; |
| 236 | YASPS: A Symbolic Framework for Extensible, High-Performance IPC Simulation Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Adding new energies or alternative parameterizations often requires re-deriving first and second-order derivatives, and implementing new assembly logic for the global Hessian and gradient. This challenge is further exacerbated by collision energies, where the same energy definition is often applied to mixed parameterizations, which can lead to a combinatorial explosion of parameterization-specific derivative and assembly cases.In this paper we introduce YASPS, a framework for physical simulation that resolves this limitation by making structural relationships explicit in a differentiable representation. |
Xuan Tang; Kemeng Huang; Gilbert Bernstein; Minchen Li; Tzumao Li; |
| 237 | SAND: Spatially Adaptive Network Depth for Fast Sampling of Neural Implicit Surfaces Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: However, conventional neural implicit models evaluate all query points with the same network depth and computational cost, ignoring this spatial variation and thereby incurring substantial computational waste. Motivated by this observation, we propose an efficient neural implicit geometry representation framework with spatially adaptive network depth (SAND). |
Chuanxiang Yang; Junhui Hou; Yuan Liu; Siyu Ren; Guangshun Wei; Taku Komura; Yuanfeng Zhou; Wenping Wang; |
| 238 | NeuBase: Spline Surfaces with Neural Basis Functions Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We introduce NeuBase, a neural parametric surface representation that both accurately fits target surfaces with fine geometric detail and supports intuitive real time surface deformation. |
Anshul Mendiratta; Lei Yang; Xin Li; John Keyser; Scott Schaefer; Wenping Wang; |
| 239 | ProXeek: Seeking and Leveraging Real-World Objects and Environments As Haptic Proxies for Virtual Reality Through Multimodal Reasoning Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We present ProXeek, an LLM-based multi-agent system that opportunistically leverages real-world objects as haptic proxies for VR experiences. |
Haichen Gao; Tianrui Hu; Zeshui Li; Kening Zhu; |
| 240 | MAOAM: Unified Object and Material Selection with Vision-Language Models Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this work, we thus present Mask Any Object And Material (MAOAM), a unified selection framework that enables precise object- and material-level selection across both text- and click-based interactions. |
Jaden Park; Valentin Deschaintre; Jason Kuen; Kangning Liu; Iliyan Georgiev; Krishna Kumar Singh; Yong Jae Lee; Michael Fischer; |
| 241 | LightOpt: Lights Optimization for Real-time Rendering Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We present a differentiable lighting optimization pipeline that automatically reduces the number of active lights while preserving the final rendered appearance. |
Tuo Chen; Luyan Cao; Kui Wu; Shimin Hu; |
| 242 | Neural Quadrature Rule and Autoregressive Adaptive Sampling Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: To address these limitations, we argue that a sampler and integrator beyond the standard Monte Carlo methods is needed. We therefore propose an end-to-end sampling-integration approach that jointly learns both a sampler and an integrator using neural networks, enabling samples to be drawn and used in a more coupled and principled manner. |
Haolin Lu; Liwen Wu; Zimo Wang; Tzu-Mao Li; Ravi Ramamoorthi; |
| 243 | Flatten The Complex: Joint B-Rep Generation Via Compositional K-Cell Particles Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Previous methods typically rely on cascaded sequences to handle this hierarchy, which fails to fully exploit the geometric relationships between cells, such as adjacency and sharing, limiting context awareness and error recovery. To fill this gap, we introduce a novel paradigm that reformulates B-Reps into sets of compositional k-cell particles (KCPs). |
Junran Lu; Yuanqi Li; Hengji Li; Jie Guo; Yanwen Guo; |
| 244 | Real-Time GPU Vector Graphics SDF Generation Based on Quadratic Stroke Rendering Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: This paper introduces a novel, GPU-accelerated algorithm that reframes SDF generation as a parallel quadratic stroke rendering problem. |
Xuhai Chen; Guangze Zhang; Juan Cao; Zhonggui Chen; |
| 245 | High-Fidelity 4D Cloth Capture Pipeline with A Two-Level Pattern Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We present a 4D (spatio-temporal) cloth capture system that achieves 1 mm spatial resolution using only 16 RGB cameras. |
Ziheng Liu; Anka Chen; Shu Chen; Yin Yang; Cem Yuksel; Jenny Han Lin; |
| 246 | Statistical Gradient Filtering for Geometry Optimization Under Limited Observations Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: However, such smoothness alone propagates gradients to unobserved regions without any prior knowledge of how shapes typically deform in a given domain. We introduce statistical gradient filtering, which leverages statistical structure across a shape collection by learning shape variations via principal component analysis (PCA) and guiding geometry updates along directions consistent with this learned prior. |
Wonjong Jang; Gwangjin Ju; Seungyong Lee; |
| 247 | UCM: Unified Modeling of Camera Control and Memory with Time-aware Positional Encoding Warping for World Models Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Alternative methods rely directly on previously generated frames without establishing explicit spatial correspondence, thereby limiting controllability and consistency. To address these limitations, we present UCM, a novel framework for unified modeling of long-term memory and precise camera control via a time-aware positional encoding warping mechanism. |
Tian-Xing Xu; Zi-Xuan Wang; Guangyuan Wang; Li Hu; Zhongyi Zhang; Peng Zhang; Bang Zhang; Song-Hai Zhang; |
| 248 | Atmospheric Haptics: Rendering Airflow and Temperature As Tactile Fields for Interactive Experiences in Virtual Reality Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: This paper introduces Atmospheric Haptics, a paradigm treating air and temperature as programmable, non-contact haptic fields authored through four perceptual primitives: Intensity, Temperature, Spatiality, and Dynamics. |
Shengyi Zhan; Xueting Wu; Ning Zou; |
| 249 | Learning View-Dependent Splatting Kernels Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We present a differentiable framework to automatically learn view-dependent 2D kernels in a splatting-based pipeline to improve reconstruction quality and representation efficiency for novel 3D view synthesis. |
Huakeng Ding; Zhanpeng Liu; Fan Pei; Kun Zhou; Hongzhi Wu; |
| 250 | Locality-Aware Automatic Differentiation on The GPU for Mesh-Based Computations Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We present a GPU-based system for automatic differentiation (AD) of functions defined on triangle meshes, designed to exploit the locality and sparsity in mesh-based computation. |
Ahmed Mahmoud; Rahul Goel; Jonathan Ragan-Kelley; Justin Solomon; |
| 251 | Uniformly Deployable Kirigami on Arbitrary Planar Graphs Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We present an analytical framework for exploring the design space of hinged kirigami structures that deploy rigidly and uniformly. |
Aviv Segall; Jing Ren; Olga Sorkine-Hornung; |
| 252 | Photons \texttimes{} Force: Differentiable Radiation Pressure Modeling Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We propose a system to optimize parametric designs subject to radiation pressure, i.e., the effect of light on the motion of objects. |
Charles Constant; Santosh Bhattarai; Elizabeth Bates; Marek Ziebart; Tobias Ritschel; |
| 253 | ToF ReSTIR: Time-of-Flight Rendering with Spatio-temporal Reservoir Resampling Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We present a novel spatio-temporal reuse framework for time-resolved light transport, enabling efficient Monte Carlo rendering of time-of-flight (ToF) phenomena such as time-gated imaging and transient light capture. |
Juhyeon Kim; Wojciech Jarosz; Adithya Pediredla; |
| 254 | Schr\{o}dinger Bridges on Discretized Geometric Domains Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We introduce a spatially discrete formulation of the Schr\{o}dinger bridge problem on meshes and grids that enables structure-preserving and scalable interpolation between probability distributions. |
Leticia Mattos Da Silva; Mohammad Sina Nabizadeh; Justin Solomon; |
| 255 | Explicit Flows for Implicit Surfaces Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this paper, we propose a method that provides an explicit expression of the deformation parameterized as a flow, for continuously deforming shapes defined implicitly. |
Camille Buonomo; Julie Digne; Rapha\{e}lle Chaine; |
| 256 | Constant Mean Curvature Surfaces from Discrete Harmonic Maps Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We present a straightforward discretization of constant mean curvature surfaces based on the classical observation that their Gau\ss{} maps are harmonic. |
Yousuf Soliman; Peter Schr\{o}der; Ulrich Pinkall; |
| 257 | Woodstock: Interactive Modeling of Fungal Wood Decay Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We propose a novel approach to simulate the dynamic interactions between the biological and mechanical components of wood decay, including fungal colonization, chemical defense, and moisture-driven fracture. |
Zhanyu Yang; Nikolas Schwarz; Bosheng Li; Dominik Michels; Bedrich Benes; S\{o}ren Pirk; Wojtek Palubicki; |
| 258 | CubePart: An Open-Vocabulary Part-Controllable 3D Generator Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We present CubePart, a generative framework for open-vocabulary, part-controllable 3D mesh generation that exposes part structure as an explicit inference-time control signal. |
Yiheng Zhu; Kangle Deng; Jean-Philippe Fauconnier; Inaki Navarro; Daiqing Li; Ava Pun; Yinan Zhang; Peiye Zhuang; Xiaoxia Sun; Maneesh Agrawala; Kiran Bhat; Tinghui Zhou; |
| 259 | Broadband Hyperspectral 3D Imaging Using Dispersed Structured Light Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Hyperspectral 3D imaging enables the capture of dense spectral information and scene geometry but has traditionally been confined to narrow spectral windows, typically the visible range. In this work, we introduce a broadband hyperspectral 3D imaging (BH3D) method to extend this capability across the full visible-near-infrared and short-wavelength infrared (SWIR) spectrum (450–1500 nm). |
Suhyun Shin; Yunseong Moon; Ryota Maeda; David B. Lindell; Kiriakos N. Kutulakos; Seung-Hwan Baek; |
| 260 | Ragged Neighborhood Attention for Spatiotemporal Neural Denoising of Deep Monte Carlo Renderings Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We introduce the ragged neighborhood attention (RaNA) operator, which extends neighborhood attention to semi-structured deep images by dynamically resolving bin-to-bin relationships across spatial and temporal neighborhoods. |
Xianyao Zhang; Gerhard R\{o}thlin; Tunc Ozan Aydin; Farnood Salehi; Marios Papas; |
| 261 | HairPort: In-context 3D-aware Hair Import and Transfer for Images Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Most prior works operate best under small pose gaps, and they fall short under large viewpoint and scale differences, where missing hair content must be synthesized rather than transferred. We propose HairPort, a 3D-aware hairstyle transfer framework that attempts to solve these issues by explicitly separating hair removal from transfer and enforcing geometric consistency before synthesis. |
Alireza Heidari; Amirhossein Alimohammadi; Ali Mahdavi-Amiri; |
| 262 | Colorful-Noise: Training-Free Low-Frequency Noise Manipulation for Color-Based Conditional Image Generation Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this work, we investigate the characteristics of the input noise in diffusion models. |
Nadav Z. Cohen; Ofir Abramovich; Ariel Shamir; |
| 263 | Beyond Positional Encoding: A 5D Spatio-Directional Hash Encoding Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this work, we propose a new spatio-directional neural encoding that is compact and efficient, and supports all-frequency signals in both space and direction. |
Philippe Weier; Lukas Bode; Philipp Slusallek; Adri\'{a}n Jarabo; S\'{e}bastien Speierer; |
| 264 | GR3EN: Generative Relighting for 3D Environments Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We present a method for relighting 3D reconstructions of large room-scale environments. |
Xiaoyan Xing; Philipp Henzler; Junhwa Hur; Runze Li; Jonathan T. Barron; Pratul P. Srinivasan; Dor Verbin; |
| 265 | Ambient-robust Inverse Rendering Using Active RGB-NIR Imaging Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Here we introduce an ambient-robust inverse rendering method enabled by active RGB–NIR imaging. |
Hoon-Gyu Chung; Jinnyeong Kim; Hyunwoo Kang; Seung-Hwan Baek; |
| 266 | Progressive Photorealistic Simplification Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this work, we explore a complementary direction: simplifying images while preserving their photorealistic appearance. |
Adi Rosenthal; Dana Berman; Yedid Hoshen; Ariel Shamir; |
| 267 | Invisible Holographic Window: Full-color 3D Image Reconstruction from Transparent Surface-relief Computer-generated Holograms Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: However, DOEs exhibit limited wavelength selectivity, interacting with a broad spectral range beyond their design wavelength. This results in reduced overall transmittance and typically requires three separate CGHs for full-color reconstruction.In this work, we present an invisible holographic window, a transparent, surface-relief CGH patterned directly on glass via laser grayscale lithography. |
Ryo Higashida; Masato Miura; Teruyoshi Nobukawa; Yuta Yamaguchi; Ken-ichi Aoshima; Nobuhiko Funabashi; Masahiro Yamaguchi; |
| 268 | Spatially Accelerated Winding Numbers for Curved Geometry Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We extend support for fast GWN evaluation over arbitrary collections of NURBS curves in 2D and trimmed NURBS patches in 3D via a Bounding Volume Hierarchy that stores efficiently precomputed moment data in the hierarchy nodes. |
Jacob Spainhour; Brad Whitlock; Kenneth Weiss; |
| 269 | Gaussian Point Splatting Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We propose Gaussian point splatting, a stochastic method to render Gaussian splats that scales extremely well to scenes with many Gaussians. |
Joris Rijsdijk; Christoph Peters; Michael Weinmann; Ricardo Marroquim; |
| 270 | AtomSlicer: Constant-Thickness Field-Aligned Non-Planar Slicing and Continuous Toolpaths for FFF Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Unlike prior methods it treats user- or optimizer-defined fields as constraints, producing a feasible toolpath or reporting non-fabricability rather than modifying the specification. |
Giovanni Cocco; Vincent Belle; Eric Garner; Sylvain Lefebvre; Xavier Chermain; |
| 271 | SCom DAG: Compact Representation of Spatial Data for Real-time Rendering Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We developed a new data structure for the efficient representation of spatial data, called SCom DAG — Similarity Compressed Directed Acyclic Graph. |
Albert Garifullin; Nikolay Mayorov; Eduard Hauer; Alexey Voloboy; Vladimir Frolov; |
| 272 | RCGP: Resource Contracts for Graphics Programming Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: As a result, contract breaches are often detected too late, at runtime by validation layers, or worse, as visual artifacts in rendered output.In this work, we present RCGP1, a system that mechanistically enforces resource contracts between components of a graphics program. |
Venkataram Sivaram; Sai Praveen Bangaru; Ravi Ramamoorthi; Tzu-Mao Li; Jonathan Ragan-Kelley; Fredo Durand; |
| 273 | Stochastic Geomorphological Transport for Terrain Erosion Simulation Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: A key challenge in erosion modeling is the simultaneous simulation of transport and erosive processes, which differ in temporal scales by several orders of magnitude. We address this challenge with a novel, parallel, stochastic particle-based method capable of simulating transport over geological timescales. |
Nicholas McDonald; Guillaume Cordonnier; |
| 274 | Mixwell: Sharp 2D Fluid Brushes for Progressive Physics-Based Mixing Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We present Mixwell, a family of sharp 2D fluid brushes and GPU-accelerated analytical methods for progressive, resolution-independent physics-based mixing. |
Doug James; Ethan James; |
| 275 | MotionBricks: Scalable Real-Time Motions with Modular Latent Generative Model and Smart Primitives Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this work, we identify two key challenges in bridging research and production: 1) Real-time scalability: Industry applications demand real-time generation of a vast repertoire of motion skills, while generative methods exhibit significant degradation in quality and scalability under real-time computation constraints, and 2) Integration: Industry applications demand fine-grained multi-modal control involving velocity commands, style selection, and precise keyframes, a need largely unmet by existing text- or tag-driven models. |
Tingwu Wang; Olivier Dionne; Michael De Ruyter; David Minor; Davis Rempe; Kaifeng Zhao; Mathis Petrovich; Ye Yuan; Chenran Li; Zhengyi Luo; Brian Robison; Xavier Blackwell; Bernardo Antoniazzi; Xue Bing Peng; Yuke Zhu; Simon Yuen; |
| 276 | Stress-Aware Panelization of Freeform Surfaces Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Our goal is to compute panelizations that are both geometrically faithful and structurally robust. |
Xinzhuo Hu; Roi Poranne; Julian Panetta; |
| 277 | Forget Superresolution, Sample Adaptively (when Path Tracing) Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We introduce an end-to-end adaptive sampling and denoising pipeline explicitly designed for the sub-1-spp regime. |
Martin Balint; Corentin Sala\{u}n; Hans-Peter Seidel; Karol Myszkowski; |
| 278 | Efficient Fur and Hair Multiple Scattering Using Volumetric Approximation Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this paper, we propose an efficient method for hair and fur rendering that approximates multiple scattering as volumetric light transport, achieving near path-traced visual fidelity at a drastically reduced cost. |
Ruike Hu; Junqiu Zhu; Minghao Lin; Ruian Zhang; Lu Wang; Jie Guo; Yanwen Guo; Lingqi Yan; |
| 279 | STyMo: Fast and Controllable Few-Shot Motion Style Transfer Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We present STyMo, a few-shot approach that learns motion style from only seconds of paired data and trains in one to two minutes. |
Jose Luis Ponton; Alexander Winkler; Ladislav Kavan; Yuting Ye; Petr Kadlecek; |
| 280 | Skinned Motion Retargeting with Spatially Adaptive Interaction Guidance Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this paper, we present a geometry-aware motion retargeting framework that preserves interaction semantics by performing proximity matching over spatially adaptive anchors. |
Soojin Choi; Seokhyeon Hong; Chaelin Kim; Junghyun Nam; Junhyuk Jeon; Junyong Noh; |
| 281 | ReActor: Reinforcement Learning for Physics-Aware Motion Retargeting Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We propose a bilevel optimization framework that jointly adapts reference motions to a robot’s morphology while training a tracking policy using reinforcement learning. |
David M\{u}ller; Agon Serifi; Sammy Christen; Ruben Grandia; Espen Knoop; Moritz B\{a}cher; |
| 282 | Pixels2Peaks: Converting Terrain Images to Heightmaps Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In the case of the bare-earth terrain, this is typically a manual process since, unlike for trees and buildings, few inverse reconstruction methods currently exist. To address this, we introduce a method for automatically inferring a detailed, consistent, and complete terrain heightmap from a single photographic image. |
Aryamaan Jain; James Gain; Guillaume Cordonnier; |
| 283 | Monte Carlo Rendering of Biharmonic Diffusion Curves Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We propose to treat the rendering of biharmonic diffusion curves as an inverse problem, in which the Dirichlet data of the Laplace equation is unknown. |
Paul Himmler; Tobias G\{u}nther; |
| 284 | Iskra: A System for Inverse Geometry Processing Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We propose a system for differentiating through solutions to geometry processing problems. |
Ana Dodik; Ahmed Mahmoud; Justin Solomon; |
| 285 | MeshFEM: A Block-accelerated Solver for Nonlinear Finite Elements Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We introduce a high-performance framework for solving nonconvex optimization problems arising in simulation and geometry processing applications. |
Haleh Mohammadian; Xinzhuo Hu; Roi Poranne; Julian Panetta; |
| 286 | A Two-Millisecond Passthrough Headset for Perceptual Studies Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Here, we introduce a video passthrough HMD, called Camsicle, which is capable of 2-millisecond e2e latency and, additionally, uses a catadioptric design to achieve perspective-correct passthrough without reprojection. |
Eric Penner; Josephine D’Angelo; Clinton Smith; Nathan Matsuda; Navaneethan Siva; Phillip Guan; |
| 287 | Monte Carlo PDE Solvers for Nonlinear Radiative Boundary Conditions Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Compared to standard linearization strategies, the proposed approach achieves significantly higher accuracy.To further address the high variance inherent in Monte Carlo estimators, we propose a heteroscedastic regression-based denoising technique specifically designed for on-boundary solution estimates, filling a gap left by prior variance reduction methods that focus solely on interior points. |
Anchang Bao; Enya Shen; Jianmin Wang; |
| 288 | Walk on Decomposed Subdomains: A Hybrid Monte Carlo–Deterministic Solver for Elliptic PDEs Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We introduce a hybrid approach that combines the geometric flexibility of Monte Carlo estimation with deterministic global solves that do not introduce additional stochastic error. |
Cl\'{e}ment Jambon; Mohammad Sina Nabizadeh; Mina Konakovi\'{c} Lukovi\'{c}; |
| 289 | Lifting Lines and Tone: Image-Space Stylization in Path-Space Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Our key observation is that image-space consistency can be achieved by establishing geometrically-driven mappings from image-space to path-space. We demonstrate this through two complementary stylizations: feature lines and tone.For feature line rendering, we introduce a conditional lifting based on partial path-space variation, where a geometric path parametrization is combined with parallel transport to preserve image-space structure under distribution effects. |
Rex West; Sayan Mukherjee; Yonghao Yue; |
| 290 | SQuadGen: Generating Simple Quad Layouts Via Chart Distance Fields Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We introduce SQUADGEN, a diffusion-based generative framework that leverages Chart Distance Fields (CDF) to synthesize simple quad layouts on 3D shapes. |
You-Kang Kong; Yang Liu; Yue Dong; Xin Tong; Heung-Yeung Shum; |
| 291 | Surface Chamfering for Robust Tetrahedral Meshing Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We present an algorithm that produces high quality tetrahedral meshes conforming with input polyhedra. |
Lorenzo Diazzi; Daniele Panozzo; Jiacheng Dai; Marco Attene; |
| 292 | Progressing Level-of-Detail Animation for Volumetric Elastodynamics Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We extend Progressive Dynamics [Zhang et al. 2024, 2025] from cloth and shells to volumetric finite elements, enabling an efficient level-of-detail (LOD) animation-design pipeline with predictive coarse-resolution previews for rapid iteration toward a final high-resolution volumetric elastodynamics animation. To achieve this, we introduce VelPro Splitter, a principled and substantially improved VelPro-type integrator [Zhang et al. 2025] that splits the current-level velocity and recombines its high-resolution component with prolonged coarse-level velocity. |
Jiayi Eris Zhang; Doug James; Danny Kaufman; |
| 293 | Implicit Minimal Surfaces for Bijective Correspondences Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We introduce an implicit representation of continuous, bijective, orientation-preserving maps between genus zero surfaces with or without boundary. |
Etienne Corman; Yousuf Soliman; Robin Magnet; Mark Gillespie; |
| 294 | Persistence-guided Prescribed Topological Simplification Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We present a new method for simplifying the topology of a 3D shape. |
Linxuan Rong; Tao Ju; |
| 295 | ADS: Random Sampling of Occupancy Functions Using Adaptive Delaunay Scaffolding Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Existing methods largely provide either one or the other of random sampling or mesh surfaces: ray shooting approaches deliver random samples with no connectivity, and grid-based methods deliver mesh surfaces but their sampling is highly biased. We propose a new method which delivers both pseudo-random OF surface samples and an isosurface mesh connecting them. |
Suzuran Takikawa; Leo Foord-Kelcey; Oliver Oxford; Nicholas Vining; Alla Sheffer; |
| 296 | Hybrid Gaussian Wang Tiles for Class-aware Authoring and Rendering Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We present a framework for synthesizing large, richly detailed scenes from multiple Gaussian Splatting exemplars using a class-aware Wang tiling formulation, building on Gaussian Splatting Wang Tiles as the underlying representation. |
Yunfan Zeng; Li Ma; Pedro V. Sander; |
| 297 | ActCam: Zero-Shot Joint Camera and 3D Motion Control for Video Generation Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We present ActCam, a zero-shot method for video generation that jointly (i) transfers character motion from a driving video into a new scene and (ii) enables per-frame control of intrinsic and extrinsic camera parameters. |
Omar El Khalifi; Thomas Rossi; Oscar Fossey; Thibault Fouque; Ulysse Mizrahi; Philip Torr; Ivan Laptev; Fabio Pizzati; Baptiste Bellot-Gurlet; |
| 298 | SuperSDF: Sparse SDF Super-Resolution for Surface Extraction Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Recent advances in surface generation from SDFs increasingly rely on learnable surface representations and direct mesh supervision. In this work, we challenge this trend and show that high-quality surface reconstruction can be achieved by learning to refine the volumetric signal itself. |
Sagar Panwar; Nissim Maruani; C\'{e}line Loscos; Mathieu Desbrun; Pierre Alliez; |
| 299 | Dual Contouring of Signed Distance Data Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We propose an algorithm to reconstruct explicit polygonal meshes from discretely sampled Signed Distance Function (SDF) data, which is especially effective at recovering sharp features. |
Xiana Carrera; Ningna Wang; Christopher Batty; Oded Stein; Silvia Sell\'{a}n; |
| 300 | IsoGami: Rigid-Deployable Kirigami Materials From Isohedral Tilings Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this work, we introduce a computational approach to explore the design space of rigid-deployable Kirigami sheets defined over isohedral tilings, a class of periodic patterns constructed from identical polygonal tiles. |
Guo Han; Juan Montes Maestre; Logan Numerow; Ronan Hinchet; Stelian Coros; Bernhard Thomaszewski; |
| 301 | Toward Richer Material Generation Via Procedural Data Enhancement Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Simple physically based rendering (PBR) materials, which combine a diffuse term with a single-lobe specular component, are commonly used for training but are insufficient to capture many important visual effects present in real materials. We present a method that enhances such simple PBR materials to more expressive ones, by augmenting the single GGX specular lobe into a layered model that captures a broader range of non-diffuse effects. |
Yunchen Yu; Jacob Munkberg; Jon Hasselgren; Chris Cummings; Steve Marschner; Andrea Weidlich; |
| 302 | InfiniteDiffusion: Bridging Learned Fidelity and Procedural Utility for Open-World Terrain Generation Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We introduce InfiniteDiffusion, a training-free algorithm that reformulates diffusion sampling for lazy and unbounded generation, bridging the fidelity of diffusion models with the properties that made procedural noise indispensable: seamless infinite extent, seed-consistency, and constant-time random access. |
Alexander Goslin; |
| 303 | Robust In-Engine Texture Optimization from Inconsistent Generative Targets Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We propose a robust texture optimization framework that handles inconsistent AI-generated targets by operating directly within non-differentiable production pipelines. |
Taejoon Kim; Seung-Uk Yoon; Seong-Jae Lim; Bon-Woo Hwang; Kinam Kim; Seung Wook Lee; |
| 304 | Buoyancy-driven Phase Separation in The Material Point Method Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We present a novel method that enables natural buoyancy-driven phase separation in weakly compressible MPM. |
Mehrnaz Ayazi; Craig Schroeder; Tamar Shinar; |
| 305 | Rao-Blackwellized Markov Chain Monte Carlo Light Transport Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In practice, however, the RB approach traditionally used in light transport, waste-recycling, can yield little to no measurable variance reduction, a fact we empirically confirm in this work. Motivated by this lack of effective variance reduction, we introduce a novel RB technique for the general-purpose Metropolis-Hastings (MH) algorithm that is computationally efficient and achieves substantial variance reduction. |
Sascha Holl; Gurprit Singh; Hans-Peter Seidel; |
| 306 | MultiAct: Text-to-Motion Generation from Composite Text Via Tailored Attention Guidance Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We present MultiAct, an unpaired, inference-time framework for compositional text-to-motion synthesis that operates directly on pretrained motion generators without retraining or architectural modification. |
Nathan Sala; Ofir Abramovich; Ariel Shamir; Daniel Cohen-Or; Andreas Aristidou; Sigal Raab; |
| 307 | Continuity-Enhancing Degree Elevation and Splits Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Cubic polynomial curve modeling with B\'{e}zier handles is ubiquitous, but it provides no practical mechanism for achieving curvature continuity. We present two distinct solutions for this problem. |
Cem Yuksel; |
| 308 | Multi-Layer Reservoir Splatting for Temporal Reuse Under Disocclusion Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We address disocclusions in ReSTIR by introducing multiple screen-space layers, using reservoir splatting to shift samples between layers. |
Pengpei Hong; Song Zhang; Daqi Lin; Markus Kettunen; Chris Wyman; Cem Yuksel; |
| 309 | Curvature Space Editing of Highly-Coiled Hair Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this work we propose using material curvatures and twists to analyze and edit tightly coiled hair styles. |
Alvin Shi; Florence Bertails-Descoubes; A.M. Darke; Theodore Kim; |
| 310 | Adaptive Interpolation-Synthesis for Motion In-Betweening on Keyframe-Based Animation Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Although recent deep learning approaches have achieved strong results in motion synthesis and in-betweening, they assume data characteristics, motion styles, and problem formulations that diverge from professional animation workflows. To bridge this gap, we propose a method explicitly aligned with the constraints of motion in-betweening for keyframe-based animation in production environments. |
Anton Ra\{e}l; Julien Boucher; Antoine Lhermitte; |
| 311 | NeuralSketch2Surf: Fast Neural Surfacing of Unoriented 3D Sketches Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We introduce NeuralSketch2Surf, the first fast and robust neural surfacing solution that processes arbitrarily unoriented sketches at interactive rates. |
Hongsheng Ye; Anandhu Sureshkumar; Zhonghan Wang; Stefanie Hahmann; Marie-Paule Cani; Georges-Pierre Bonneau; Amal Dev Parakkat; |
| 312 | Taming Optimization Variance in Compact Neural Shading Networks Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We present a training algorithm to mitigate optimization instabilities in small neural networks, like those used in real-time neural shading applications. |
Benedikt Bitterli; Petrik Clarberg; Chris Cummings; Aaron Lefohn; Steve Marschner; Jan Nov\'{a}k; Fabrice Rousselle; Andrea Weidlich; Tizian Zeltner; |
| 313 | Fast Sparse Matrix Permutation for Mesh-Based Direct Solvers Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We present a fast sparse matrix permutation algorithm tailored to linear systems arising from triangle meshes. |
Behrooz Zarebavani; Ahmed H. Mahmoud; Ana Dodik; Changcheng Yuan; Serban D. Porumbescu; John D. Owens; Maryam Mehri Dehnavi; Justin Solomon; |
| 314 | Dynamic Visual Dominance in Stereoscopic Foveation Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this work, we systematically characterize dynamic visual dominance across the visual field, with a particular focus on peripheral vision, where perceptual asymmetries are most relevant for stereoscopic rendering. |
Daniel Jim\'{e}nez-Navarro; Colin Groth; Kenneth Chen; Qi Sun; Karol Myszkowski; Hans-Peter Seidel; Ana Serrano; |
| 315 | Quantifying Reality of Ultra-realistic 3-D Displays – The Effect of Resolution and Contrast Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Developments in display technology mean that it may soon be possible to create stereoscopic 3-D imagery that cannot be distinguished from its real-world counterpart, i.e., it could pass the so-called Visual Turing Test. To measure how far current display technologies are from this ultimate goal, we built a custom ultra-realistic display — a high dynamic range (HDR) stereoscope, with accurate color and geometric calibration. |
Joseph G. March; Dounia Hammou; Simon J. Watt; Rafa\l{} K. Mantiuk; |
| 316 | It’s Not Just A Phase: Creating Phase-Aligned Peripheral Metamers Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: While this strategy avoids rendering part of the content altogether, an alternative promising direction is to replace accurate and expensive rendering with inexpensive synthesis of content that is perceptually indistinguishable from the ground-truth image. In this paper, we propose such a method for the efficient generation of an image signal that substitutes the rendering of high-frequency details. |
Sophie Kerga\ss{}ner; Piotr Didyk; |
| 317 | Walking on Spheres and Talking to Neighbors: Variance Reduction for Laplace’s Equation Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We propose a new caching strategy that leverages the continuity of paths of Brownian Motion. |
Michael Czekanski; Benjamin Faber; Margaret Fairborn; Adelle Wright; David Bindel; |
| 318 | Fast Cutting of Cage Based Deformation with Walk on Spheres Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We propose a novel reuse pipeline to efficiently update only weights subject to a topological modification. |
Hossam Saeed; Michael Lambiri; Teseo Schneider; Derek Nowrouzezahrai; Paul G. Kry; |
| 319 | Gradient Descent in The ALPS: Abstracted Low-Poly Stylization and Fabrication Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this paper, we propose a method to generate 2D low-poly meshes to abstract images. |
Ruben Wiersma; Alexandre Binninger; Peizhuo Li; Tanguy Magne; Annika Oehri; Aviv Segall; Danielle Luterbacher; Marcel Padilla; Jing Ren; Olga Sorkine-Hornung; |
| 320 | Divide and Truncate: A Penetration and Inversion Free Framework for Coupled Multi-physics System Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We present Divide and Truncate (DAT), a unified framework for coupling multi-physics systems through penetration-free collision handling, including rigid bodies, volumetric soft bodies, thin shells, rods, and animated objects. |
Anka H. Chen; Jerry Hsu; Youssef Ayman; Miles Macklin; |
| 321 | Synchronizing Fields with Singularities Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We observe that these problems can be viewed as synchronization problems, which admit a natural semidefinite relaxation. We propose a unified method of solving all these problems via the efficient Burer-Monteiro factorization method. |
Natalia Pacheco-Tallaj; Matt\'{e}o Couplet; Edward Chien; David Palmer; |
| 322 | DJM: Compact Base Meshes for Displacement Mapping Using Triangle Jacobians Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Our new DJM (Displacement Jacobian Metric)-based base-mesh construction method uses the Jacobian of the displacement functions to guide base mesh computation, enabling us to outperform prior approaches in terms of accuracy to size trade-off. We achieve this goal by proposing a variant of the QEM-based simplification scheme that constrains the displacement mapping between the input and the base to be bijective and low distortion (defined as satisfying a lower bound on the mapping Jacobian). |
Congyi Zhang; Nicholas Vining; Yanhong Lin; Alireza Khatami; Ziyu Sun; Xiaohu Guo; Wenping Wang; Alla Sheffer; |
| 323 | Tube Maps: Fast SPH Boundary Handling with Tubular Coordinates Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We introduce Tube Maps, a drop-in replacement for SPH boundary density computation that achieves accuracy comparable to implicit methods while dramatically reducing their computational cost. |
Daria Nogina; Silvia Sell\'{a}n; |
| 324 | Object-Space Analysis of Local Contrast Sensitivity for Hierarchical Representations of 3D Gaussians Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this paper, we present an object-space analysis framework of contrast sensitivity for 3D Gaussian representations. |
Naoto Yoshii; Suguru Saito; Masataka Sawayama; Yoshinori Dobashi; |
| 325 | Stylized Text-to-Motion Generation Via Hypernetwork-Driven Low-Rank Adaptation Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We propose a lightweight style conditioning framework that dynamically modulates a pretrained diffusion model through hypernetwork-generated LoRA parameters. |
Junhyuk Jeon; Seokhyeon Hong; Junyong Noh; |
| 326 | Immediate 3D Gaussian Splat Reconstruction of Unordered Input with Global Consistency Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Incremental reconstruction methods – often derived from SLAM solutions – provide immediate feedback, but cannot handle the out-of-order capture we require. We provide the first immediate feedback solution for such radiance field capture that provides global consistency. |
Andreas Meuleman; Linus Franke; Boris Zhestiankin; Camille Montemagni; George Drettakis; |
| 327 | Reciprocal Latent Fields for Precomputed Sound Propagation Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Wave coding methods address this limitation by precomputing and compressing impulse responses of a given scene into a set of scalar acoustic parameters, which can reach unmanageable sizes in large environments with many source-receiver pairs. We introduce Reciprocal Latent Fields (RLF), a memory-efficient framework for encoding and predicting these acoustic parameters. |
Hugo Seut\'{e}; Pranai Vasudev; Etienne Richan; Louis-Xavier Buffoni; |