Papers › H2ONet: Hand-Occlusion-and-Orientation-Aware Network for Real-Time 3D Hand Mesh Reconstruction

H2ONet: Hand-Occlusion-and-Orientation-Aware Network for Real-Time 3D Hand Mesh Reconstruction

1 Jan 2023CVPR 2023 1archive 2025-07-28

Hao Xu, Tianyu Wang, Xiao Tang, Chi-Wing Fu

Real-time 3D hand mesh reconstruction is challenging, especially when the hand is holding some object. Beyond the previous methods, we design H2ONet to fully exploit non-occluded information from multiple frames to boost the reconstruction quality. First, we decouple hand mesh reconstruction into two branches, one to exploit finger-level non-occluded information and the other to exploit global hand orientation, with lightweight structures to promote real-time inference. Second, we propose finger-level occlusion-aware feature fusion, leveraging predicted finger-level occlusion information as guidance to fuse finger-level information across time frames. Further, we design hand-level occlusion-aware feature fusion to fetch non-occluded information from nearby time frames. We conduct experiments on the Dex-YCB and HO3D-v2 datasets with challenging hand-object occlusion cases, manifesting that H2ONet is able to run in real-time and achieves state-of-the-art performance on both the hand mesh and pose precision. The code will be released on GitHub.

PaperPDFCode

Code

hxwork/H2ONet_Pytorch officialpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

3D Hand Pose Estimation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
3D Hand Pose Estimation DexYCB H2ONet Average MPJPE (mm) 14.0 #6 of 11 Archive leaderboard report
3D Hand Pose Estimation DexYCB H2ONet MPVPE 13.0 #6 of 11 Archive leaderboard report
3D Hand Pose Estimation DexYCB H2ONet PA-MPVPE 5.5 #6 of 11 Archive leaderboard report
3D Hand Pose Estimation DexYCB H2ONet PA-VAUC 89.1 #6 of 11 Archive leaderboard report
3D Hand Pose Estimation DexYCB H2ONet Procrustes-Aligned MPJPE 5.70 #6 of 11 Archive leaderboard report
3D Hand Pose Estimation DexYCB H2ONet VAUC 76.2 #6 of 11 Archive leaderboard report
3D Hand Pose Estimation HO-3D v2 H2ONet AUC_J 0.829 #7 of 24 Archive leaderboard report
3D Hand Pose Estimation HO-3D v2 H2ONet AUC_V 0.828 #7 of 24 Archive leaderboard report
3D Hand Pose Estimation HO-3D v2 H2ONet F@15mm 0.966 #7 of 24 Archive leaderboard report
3D Hand Pose Estimation HO-3D v2 H2ONet F@5mm 0.570 #7 of 24 Archive leaderboard report
3D Hand Pose Estimation HO-3D v2 H2ONet PA-MPJPE (mm) 8.5 #7 of 24 Archive leaderboard report
3D Hand Pose Estimation HO-3D v2 H2ONet PA-MPVPE 8.6 #7 of 24 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections