Research map / 3D vision / Human pose estimation
H2ONet: Hand-Occlusion-and-Orientation-Aware Network for Real-Time 3D Hand Mesh Reconstruction
Hao Xu, Tianyu Wang, Xiao Tang, Chi-Wing Fu
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 full multi-frame H2ONet instead of its single-frame version | H2ONet · Dex-YCB test | PA-J-PE: 5.7 -> 5.3 | Improved |
| Use the full multi-frame H2ONet instead of its single-frame version | H2ONet · HO3D-v2 test (after PA) | J-PE: 9.0 -> 8.5 | Improved |
| Add the dual-branch structure to the baseline (ablation) | H2ONet · Dex-YCB ablation | PA-J-PE: 6.36 -> 5.65 | Improved |
| Add multi-frame inputs with direct feature concatenation (ablation) | H2ONet · Dex-YCB ablation | PA-J-PE: 5.65 -> 5.57 | Improved |
| Select the result from the most non-occluded frame rather than fusing per-finger information (ablation) | H2ONet · Dex-YCB ablation | PA-J-PE: 5.57 -> 8.54 | Hurt |
| Add finger-level occlusion-aware feature fusion (ablation) | H2ONet · Dex-YCB ablation | PA-J-PE: 5.57 -> 5.31 | Improved |
| Add hand-level occlusion-aware feature fusion (ablation) | H2ONet · Dex-YCB ablation | J-PE: 13.96 -> 13.68 | Improved |
| Use multi-frame inputs with direct feature concatenation rather than the dual-branch baseline (ablation) | H2ONet · Dex-YCB ablation | J-PE: 14.02 -> 14.01 | No clear effect |
Later papers that compared with this method
5 later accepted papers report H2ONet as a baseline in their results tables; 5 of them report a better number on most of the results they share with it.
- TokenHand: Discrete Token Representation for Efficient Hand Mesh Reconstruction (CVPR 2026 · better on 1 of 1 shared result)
- MaskHand: Generative Masked Modeling for Robust Hand Mesh Reconstruction in the Wild (ICCV 2025 · better on 1 of 1 shared result)
- SiMA-Hand: Boosting 3D Hand-Mesh Reconstruction by Single-to-Multi-View Adaptation (AAAI 2024 · better on 6 of 6 shared results)
- A Simple Baseline for Efficient Hand Mesh Reconstruction (CVPR 2024 · better on 3 of 4 shared results)
- HandBooster: Boosting 3D Hand-Mesh Reconstruction by Conditional Synthesis and Sampling of Hand-Object Interactions (CVPR 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 1 of 1 on most shared results.
- HandOccNet — HandOccNet: Occlusion-Robust 3D Hand Mesh Estimation Network (CVPR 2022) · 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
- SiMA-Hand: Boosting 3D Hand-Mesh Reconstruction by Single-to-Multi-View Adaptation (AAAI 2024 · similarity 0.90)
- Fine-Grained Multi-View Hand Reconstruction Using Inverse Rendering (AAAI 2024 · similarity 0.87)
- HandBooster: Boosting 3D Hand-Mesh Reconstruction by Conditional Synthesis and Sampling of Hand-Object Interactions (CVPR 2024 · similarity 0.87)
- HandOS: 3D Hand Reconstruction in One Stage (CVPR 2025 · similarity 0.87)
- Reconstructing Hands in 3D with Transformers (CVPR 2024 · similarity 0.87)
- VTON-HandFit: Virtual Try-on for Arbitrary Hand Pose Guided by Hand Priors Embedding (CVPR 2025 · similarity 0.87)
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.
