SIGGRAPH-2026 Paper Digest

Los Angeles300+ papers~1,500 authors

Every paper, ordered by impact or potential impact. About SIGGRAPH 2026

IDPaperAuthors
1Nexus: Native Mesh Generation with Diffusion
IF:3   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 et al.
2Autoregressive Diffusion with Hybrid Representation for Interactive Human Motion Generation
IF:3   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 et al.
3SMP: Reusable Score-Matching Motion Priors for Physics-Based Character Control
IF:3   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 et al.
4Pixal3D: Pixel-Aligned 3D Generation from Images
IF:3   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 et al.
5OmniRoam: World Wandering Via Long-Horizon Panoramic Video Generation
IF:3   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 et al.

About SIGGRAPH 2026