CVAIGRJun 28

DR-GS: Physically-Based Deformable and Relightable 2D Gaussians

arXiv:2606.2937914.3
Predicted impact top 20% in CV · last 90 daysOriginality Incremental advance
AI Analysis

For VR/AR and digital content creation, DR-GS addresses the problem of physically inconsistent appearance under deformation and lighting changes, enabling post-reconstruction material editing.

DR-GS proposes a unified Gaussian framework that disentangles geometry, illumination, and material to enable physically consistent deformable and relightable 2D Gaussians, achieving leading visual quality in static reconstruction, dynamic deformation, and relighting while preserving reflections and specular highlights.

Gaussian splatting (GS) has garnered significant attention in VR/AR and digital content creation due to its explicit parameterization and efficient rendering capabilities. However, existing GS-based methods for deformable objects face two key limitations: (i) illumination is erroneously baked into textures, causing physically inconsistent responses under dynamic deformations and lighting changes; (ii) snapshot-based reconstruction restricts post-reconstruction material editing. To address these challenges, we propose Deformable and Relightable GS (DR-GS), a unified Gaussian framework that integrates physically-based inverse rendering, relighting, and deformation-aware manipulation. Through explicitly disentangling geometry, illumination, and material representations, DR-GS overcomes the limitations of static snapshots, resolving unrealistic appearance under varying conditions while enabling post-reconstruction parameter editing. Extensive experiments show that DR-GS achieves leading visual quality across static reconstruction, dynamic deformation, and relighting, reliably preserving reflections and specular highlights on glossy surfaces. It further establishes a fully decoupled geometry-illumination-material pipeline, enabling high-quality 3D asset creation and comprehensive post-editing.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes