Research map / 3D vision / Face and shape
Tavatar: Topology-Aware Gaussian Attribute Derivation for Animatable Human Avatars
Hailin Luo, Yifan Yang, Jiazhi Shu, Zixiong Huang, Qi Chen, Qing Du, Mingkui Tan
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| derive Gaussian scale and rotation analytically from mesh instead of optimizing them | Tavatar vs best baseline (IHuman) · X-Avatar | Normal error: 2.056 -> 1.772 | Improved |
| derive Gaussian attributes analytically from mesh | Tavatar vs best baseline (IHuman) · PeopleSnapshot | Normal error: 2.055 -> 1.687 | Improved |
| derive Gaussian attributes analytically from mesh | Tavatar vs best baseline (IHuman) · X-Avatar | Chamfer Distance: 0.132 -> 0.111 | Improved |
| analytic topology-aware binding vs free Gaussians (GART) on in-distribution rotations | Tavatar · PeopleSnapshot | PSNR: male-3: 30.21 (GART) vs 28.93; male-4: 27.55 vs 27.56 | Mixed |
| analytic topology-aware binding on OOD poses | Tavatar · X-Avatar | PSNR: 00016: 28.86 -> 29.03; 00017: 25.24 -> 25.24 | Mixed |
| add Face Gaussians (analytically derived) (ablation) | Tavatar · X-Avatar subject 00019 | PSNR: 26.89 -> 28.11 | Improved |
| add Vertex Gaussians (ablation) | Tavatar · X-Avatar subject 00019 | PSNR: 25.67 -> 28.11 | Improved |
| add equilateral regularization (ablation) | Tavatar · X-Avatar subject 00019 | PSNR: 27.83 -> 28.11 | Improved |
| add equilateral regularization (ablation) | Tavatar · X-Avatar subject 00019 | Normal error: 1.834 -> 1.772 | Improved |
| add Vertex Gaussians (ablation) | Tavatar · X-Avatar subject 00019 | Normal error: 2.687 -> 1.772 | Improved |
| add Face Gaussians (ablation) | Tavatar · X-Avatar subject 00019 | Normal error: 2.143 -> 1.772 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.
- GART — GART: Gaussian Articulated Template Models (CVPR 2024) · better on 3 of 5 shared results
- GomAvatar — GoMAvatar: Efficient Animatable Human Modeling from Monocular Video Using Gaussians-on-Mesh (CVPR 2024) · better on 5 of 5 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- GAvatar: Animatable 3D Gaussian Avatars with Implicit Mesh Learning (CVPR 2024 · similarity 0.91)
- GaussianAvatar: Towards Realistic Human Avatar Modeling from a Single Video via Animatable 3D Gaussians (CVPR 2024 · similarity 0.90)
- GoMAvatar: Efficient Animatable Human Modeling from Monocular Video Using Gaussians-on-Mesh (CVPR 2024 · similarity 0.89)
- GaussianAvatars: Photorealistic Head Avatars with Rigged 3D Gaussians (CVPR 2024 · similarity 0.89)
- MPMAvatar: Learning 3D Gaussian Avatars with Accurate and Robust Physics-Based Dynamics (NeurIPS 2025 · similarity 0.89)
- 3DGS-Avatar: Animatable Avatars via Deformable 3D Gaussian Splatting (CVPR 2024 · 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.
