Research map / 3D vision / Face and shape
Vid2Avatar: 3D Avatar Reconstruction From Videos in the Wild via Self-Supervised Scene Decomposition
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 |
|---|---|---|---|
| Add the scene decomposition loss (ablation) | Vid2Avatar · MonoPerfCap | IoU: 0.942 -> 0.961 | Helped |
| Add joint optimization of pose, shape, and appearance (ablation) | Vid2Avatar · 3DPW | Normal consistency: 0.737 -> 0.753 | Helped |
| Model the background jointly with the human (ablation) | Vid2Avatar · 3DPW | Chamfer distance (cm): 3.13 -> 2.66 | Helped |
| Use self-supervised 3D scene decomposition rather than an external segmentation tool | Vid2Avatar · MonoPerfCap | IoU: 0.950 -> 0.961 | Helped |
| Use Vid2Avatar instead of SelfRecon | human surface reconstruction · SynWild | IoU: 0.805 -> 0.813 | Helped |
| Use Vid2Avatar instead of HumanNeRF | novel view synthesis · NeuMan test views | SSIM: 0.963 -> 0.964 | Helped |
| Use Vid2Avatar instead of HumanNeRF | novel view synthesis · NeuMan test views | PSNR: 24.8 -> 25.1 | Helped |
Closest papers by meaning
- Vid2Avatar-Pro: Authentic Avatar from Videos in the Wild via Universal Prior (CVPR 2025 · similarity 0.93)
- MultiPly: Reconstruction of Multiple People from Monocular Video in the Wild (CVPR 2024 · similarity 0.90)
- WildAvatar: Learning In-the-wild 3D Avatars from the Web (CVPR 2025 · similarity 0.90)
- FRESA: Feedforward Reconstruction of Personalized Skinned Avatars from Few Images (CVPR 2025 · similarity 0.89)
- GeoAvatar: Geometrically-Consistent Multi-Person Avatar Reconstruction from Sparse Multi-View Videos (CVPR 2025 · similarity 0.89)
- ODHSR: Online Dense 3D Reconstruction of Humans and Scenes from Monocular Videos (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.