Research map / 3D vision / Face and shape
X-Avatar: Expressive Human Avatars
Kaiyue Shen, Chen Guo, Manuel Kaufmann, Juan Jose Zarate, Julien Valentin, Jie Song, Otmar Hilliges
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 |
|---|---|---|---|
| Use X-Avatar's part-aware implicit avatar instead of SNARF | Avatar animation · GRAB | CD (All): 1.37 -> 0.94 | Improved |
| Use X-Avatar's part-aware implicit avatar instead of the strongest listed baseline | Avatar animation · X-Humans (Scans) | CD (All): 5.05 -> 4.43 | Improved |
| Use X-Avatar's expressive avatar instead of PINA | RGB-D avatar animation · X-Humans (RGB-D) | CD (Hands): 9.51 -> 5.27 | Improved |
| Add hand and face bones to correspondence-search initialization rather than using body bones only (ablation) | X-Avatar · X-Humans (Scans) | CD (Hands): 5.05 -> 4.15 | Improved |
| Use part-aware initialization instead of initializing with all bones naively (ablation) | X-Avatar · X-Humans (Scans) | training speed: 0.25 -> 0.7 iterations per second | Improved |
| Add part-aware sampling rather than uniform sampling (ablation) | X-Avatar · X-Humans (Scans) | CD (Hands): 4.81 -> 4.15 | Improved |
| Add SMPL-X LBS-weight regularization for hands and face (ablation) | X-Avatar · X-Humans (Scans) | CD (Hands): 7.27 -> 4.15 | Improved |
Later papers that compared with this method
3 later accepted papers report X-Avatar as a baseline in their results tables; 3 of them report a better number on most of the results they share with it.
- FastAnimate: Towards Learnable Template Construction and Pose Deformation for Fast 3D Human Avatar Animation (AAAI 2026 · better on 6 of 6 shared results)
- CtrlAvatar: Controllable Avatars Generation via Disentangled Invertible Networks (AAAI 2025 · better on 7 of 10 shared results)
- Expressive Whole-Body 3D Gaussian Avatar (ECCV 2024 · better on 3 of 3 shared results)
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.
- PINA — PINA: Learning a Personalized Implicit Neural Avatar From a Single RGB-D Video Sequence (CVPR 2022) · better on 2 of 2 shared results
- SCANimate — SCANimate: Weakly Supervised Learning of Skinned Clothed Avatar Networks (CVPR 2021) · better on 1 of 1 shared result
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
- Expressive Gaussian Human Avatars from Monocular RGB Video (NeurIPS 2024 · similarity 0.91)
- RAM-Avatar: Real-time Photo-Realistic Avatar from Monocular Videos with Full-body Control (CVPR 2024 · similarity 0.90)
- FRESA: Feedforward Reconstruction of Personalized Skinned Avatars from Few Images (CVPR 2025 · similarity 0.89)
- CtrlAvatar: Controllable Avatars Generation via Disentangled Invertible Networks (AAAI 2025 · similarity 0.88)
- AvatarGO: Zero-shot 4D Human-Object Interaction Generation and Animation (ICLR 2025 · similarity 0.88)
- Vid2Avatar-Pro: Authentic Avatar from Videos in the Wild via Universal Prior (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.
