Research map / 3D vision / Face and shape
PINA: Learning a Personalized Implicit Neural Avatar From a Single RGB-D Video Sequence
Zijian Dong, Chen Guo, Jie Song, Xu Chen, Andreas Geiger, Otmar Hilliges
Check 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 PINA's joint canonical-space sequence fusion instead of framewise reconstruction | Human reconstruction on BUFF · BUFF | IoU: 0.783 -> 0 . 8 7 9 | Improved |
| Use PINA's joint canonical-space sequence fusion instead of framewise reconstruction | Human reconstruction on BUFF · BUFF | Chamfer distance (cm): 2.1 -> 1.1 | Improved |
| Use PINA's joint canonical-space sequence fusion instead of framewise reconstruction | Human reconstruction on BUFF · BUFF | Normal consistency: 0.861 -> 0 . 9 2 7 | Improved |
| Use PINA with partial 2.5D input instead of SCANimate (2.5D) | Animation · CAPE | IoU: 0.665 -> 0.946 | Improved |
| Use PINA with partial 2.5D input instead of SCANimate (2.5D) | Animation · CAPE | Chamfer distance (cm): 3.704 -> 0.666 | Improved |
| Use PINA with partial 2.5D input instead of SCANimate (2.5D) | Animation · CAPE | Normal consistency: 0.785 -> 0.906 | Improved |
| Disable joint pose optimization (ablation) | PINA · BUFF | IoU: 0.879 -> 0.850 | Hurt |
| Disable joint pose optimization (ablation) | PINA · BUFF | Chamfer distance (cm): 1.1 -> 1.6 | Hurt |
| Disable joint pose optimization (ablation) | PINA · BUFF | Normal consistency: 0 . 9 2 7 -> 0.887 | Hurt |
| Remove pose conditioning from the shape network (ablation) | PINA · CAPE | Chamfer distance (cm): 0.604 -> 0.991 | Hurt |
| Replace learned skinning weights with SMPL weights (ablation) | PINA · CAPE | Normal consistency: 0.912 -> 0.887 | Hurt |
Later papers that compared with this method
2 later accepted papers report PINA as a baseline in their results tables; 2 of them report a better number on most of the results they share with it.
- NSF: Neural Surface Fields for Human Modeling from Monocular Depth (ICCV 2023 · better on 3 of 5 shared results)
- X-Avatar: Expressive Human Avatars (CVPR 2023 · better on 2 of 2 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
- MetaAvatar: Learning Animatable Clothed Human Models from Few Depth Images (NeurIPS 2021 · similarity 0.89)
- FRESA: Feedforward Reconstruction of Personalized Skinned Avatars from Few Images (CVPR 2025 · similarity 0.88)
- Pose Modulated Avatars from Video (ICLR 2024 · similarity 0.88)
- NECA: Neural Customizable Human Avatar (CVPR 2024 · similarity 0.87)
- RAM-Avatar: Real-time Photo-Realistic Avatar from Monocular Videos with Full-body Control (CVPR 2024 · similarity 0.87)
- 3DGS-Avatar: Animatable Avatars via Deformable 3D Gaussian Splatting (CVPR 2024 · similarity 0.86)
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.
