Graphics Papers of the Week

A standardized sampling framework included 100 white-roof and 100 lower-reflectivity brown-roof regions of interest (ROIs) per city.

However, differences in voxel values and opacity across transfer functions can make a fixed setting produce underexposed or overexposed results. To address this issue, we propose a voxel-contribution-based adaptive exposure model for physically based volume rendering.

This study addresses the multi-objective trade-off between daylight utilization and reductions in the annual spatial-mean DGP indicator in office spaces in cold regions.

However, prevailing completion methods prioritize global structural patterns while neglecting entity role dependencies and type-level semantic priors, rendering them vulnerable to data sparsity and semantic noise. This study proposes RATA, a hyper-relational knowledge graph completion model that integrates role-aware and type-aware mechanisms to mitigate these drawbacks.

Topological transformations of their band structure can give rise to flatbands, which host dispersionless states with quenched kinetic energy and vanishing group velocity. Here we show that structuring ReS 2 into a resonant metasurface reshapes its photonic band topology, splitting the integer topological charge of the quasi-bound states in the continuum into two half-integer polarization singularities and driving the formation of directional far-field flatbands.

Abstract This state‐of‐the‐art report provides an overview of controllable 3D human avatar creation.

This survey presents a structured narrative synthesis of image, video, audio, and multimodal generation and detection, organised around the relationship between synthesis mechanisms and forensic evidence.

In this paper, we introduce a new task - semantic-aware shape abstraction, where the goal is to produce abstractions that are both geometrically faithful and semantically consistent, ensuring that each primitive adheres strictly to a single semantic part without crossing semantic boundaries.

On TikTok and UBC Fashion, the adapted model improves the base on every metric, inverts the identity-versus-motion trade-off, and matches or surpasses adaptation on five real frames despite using none.

By analyzing a publicly available genome-wide CRISPR-Cas9 screen conducted in the presence of the PARP inhibitor niraparib, we identified DKC1 as a top candidate whose loss synergized with PARP inhibition to selectively kill HR-proficient cancer cells.

However, extracting an object from a source scene and naively pasting it into a target scene will fail to produce realistic results due to the different lighting conditions between the two scenes. To address this problem, we introduce a diffusion model that harmonizes naively composited images with inconsistent lighting.

This work introduces CtrlFlow, a single-pass guidance method that preserves CFG's separable base-flow and guidance-direction interface.

We propose DC-SQEM, a dual-contouring-based framework that computes medial meshes (an explicit representation of the medial axis) directly from oriented point clouds without relying on watertight manifold surfaces or volumetric structures.

To address the god-agent problem, this paper proposes a fine-grained modular architectural pattern for implementing agents and MASs that systematically separates functional concerns into independently managed aspect entities while preserving the logical identity of agents within a standalone environment.

We present GazeTags, a camera- and computer-vision-free approach for worn head-gaze object awareness.

We present GaussianRenderFormer, a transformer that takes a set of Gaussians and a camera and outputs the image directly.

We present EDGAR (Efficient Diffusion-Driven Gaussian Avatar Refinement), a conditional diffusion framework designed to enhance the quality of Gaussian avatars by correcting artifacts while preserving identity fidelity.