Research map / 3D vision / Gaussian splatting
TGA: True-to-Geometry Avatar Dynamic Reconstruction
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's abstract only. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Proposes TGA, a 3D Gaussian Splatting-based dynamic avatar reconstruction method aimed at capturing intricate facial geometry under subtle skin-tone appearance changes.
Problem
Dynamic avatar reconstruction with 3DGS often fails to capture fine facial geometry because skin tones are chromatically similar and the affine approximation of Gaussian projection is not perspective-aware to depth-induced shading changes.
Approach
Addresses the affine approximation error of Gaussian projection by making the rendering perspective-aware to depth-induced shading variation, so that subtle appearance changes on skin encode geometry (details beyond the abstract are not available).
Experimental setup
Builds on: 3D Gaussian Splatting
Closest papers by meaning
- Gaussian Head Avatar: Ultra High-fidelity Head Avatar via Dynamic Gaussians (CVPR 2024 · similarity 0.89)
- Dynamic Gaussians Mesh: Consistent Mesh Reconstruction from Dynamic Scenes (ICLR 2025 · similarity 0.89)
- 3D Gaussian Head Avatars with Expressive Dynamic Appearances by Compact Tensorial Representations (CVPR 2025 · similarity 0.88)
- 3DGS-Avatar: Animatable Avatars via Deformable 3D Gaussian Splatting (CVPR 2024 · similarity 0.88)
- Creating Your Editable 3D Photorealistic Avatar with Tetrahedron-constrained Gaussian Splatting (CVPR 2025 · similarity 0.88)
- GPAvatar: High-fidelity Head Avatars by Learning Efficient Gaussian Projections (CVPR 2025 · similarity 0.88)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.