Research map / 3D vision / Face and shape
Hand Avatar: Free-Pose Hand Animation and Rendering From Monocular Video
Xingyu Chen, Baoyuan Wang, Heung-Yeung Shum
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 the local-pair decoder instead of COAP decoding | Hand geometry occupancy field · InterHand2.6M geometry | IoU (%): 95.08 -> 96.32 | Improved |
| Use a Transformer-based decoder instead of the local-pair decoder (ablation) | PairOF · InterHand2.6M geometry | IoU (%): 96.32 -> 96.06 | Hurt |
| Replace MANO with MANO-HD as the guided mesh | COAP · InterHand2.6M geometry | Cham.: 8.564 -> 7.694 | Improved |
| Add learned personalized shape fitting instead of β-based fitting (ablation) | HandAvatar · InterHand2.6M test/Capture0 | LPIPS: 0.1268 -> 0.1113 | Improved |
| Add the illumination field (ablation) | HandAvatar · InterHand2.6M test/Capture0 | LPIPS: 0.1113 -> 0.1063 | Improved |
| Add directed soft occupancy (ablation) | HandAvatar SelF · InterHand2.6M test/Capture0 | LPIPS: 0.1063 -> 0.1035 | Improved |
| Use HandAvatar instead of HumanNeRF | Monocular hand rendering · InterHand2.6M test/Capture0 | LPIPS: 0.1145 -> 0.1035 | Improved |
| Use HandAvatar instead of SelfRecon | Monocular hand rendering · InterHand2.6M test/Capture0 | LPIPS: 0.1421 -> 0.1035 | Improved |
Later papers that compared with this method
1 later accepted paper reports HandAvatar as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.
- HandSCS: Structural Coordinate Space for Animatable Hand Gaussian Splatting (ECCV 2026 · better on 4 of 4 shared results)
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 3 of 3 on most shared results.
- HumanNeRF — HumanNeRF: Efficiently Generated Human Radiance Field From Sparse Inputs (CVPR 2022) · better on 5 of 5 shared results
- SelfRecon — SelfRecon: Self Reconstruction Your Digital Avatar From Monocular Video (CVPR 2022) · better on 5 of 5 shared results
- COAP — COAP: Compositional Articulated Occupancy of People (CVPR 2022) · 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
- OHTA: One-shot Hand Avatar via Data-driven Implicit Priors (CVPR 2024 · similarity 0.87)
- Learning Interaction-aware 3D Gaussian Splatting for One-shot Hand Avatars (NeurIPS 2024 · similarity 0.87)
- Fine-Grained Multi-View Hand Reconstruction Using Inverse Rendering (AAAI 2024 · similarity 0.87)
- Single-view Image to Novel-view Generation for Hand-Object Interactions (AAAI 2025 · similarity 0.87)
- BiTT: Bi-directional Texture Reconstruction of Interacting Two Hands from a Single Image (CVPR 2024 · similarity 0.87)
- HandBooster: Boosting 3D Hand-Mesh Reconstruction by Conditional Synthesis and Sampling of Hand-Object Interactions (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.
