Papers › Semi-Supervised 3D Hand-Object Poses Estimation with Interactions in Time

Semi-Supervised 3D Hand-Object Poses Estimation with Interactions in Time

9 Jun 2021CVPR 2021 1arXiv:2106.05266archive 2025-07-28

Shaowei Liu, Hanwen Jiang, Jiarui Xu, Sifei Liu, Xiaolong Wang

Estimating 3D hand and object pose from a single image is an extremely challenging problem: hands and objects are often self-occluded during interactions, and the 3D annotations are scarce as even humans cannot directly label the ground-truths from a single image perfectly. To tackle these challenges, we propose a unified framework for estimating the 3D hand and object poses with semi-supervised learning. We build a joint learning framework where we perform explicit contextual reasoning between hand and object representations by a Transformer. Going beyond limited 3D annotations in a single image, we leverage the spatial-temporal consistency in large-scale hand-object videos as a constraint for generating pseudo labels in semi-supervised learning. Our method not only improves hand pose estimation in challenging real-world dataset, but also substantially improve the object pose which has fewer ground-truths per instance. By training with large-scale diverse videos, our model also generalizes better across multiple out-of-domain datasets. Project page and code: https://stevenlsw.github.io/Semi-Hand-Object

PaperPDFConference PDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

stevenlsw/Semi-Hand-Object officialmentioned on GitHubpytorch 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 EstimationHand Pose EstimationObjectPose Estimationhand-object pose

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
3D Hand Pose Estimation DexYCB SHO Average MPJPE (mm) 15.2 #9 of 11 Archive leaderboard report
3D Hand Pose Estimation DexYCB SHO MPVPE - #9 of 11 Archive leaderboard report
3D Hand Pose Estimation DexYCB SHO PA-MPVPE - #9 of 11 Archive leaderboard report
3D Hand Pose Estimation DexYCB SHO PA-VAUC - #9 of 11 Archive leaderboard report
3D Hand Pose Estimation DexYCB SHO Procrustes-Aligned MPJPE 6.58 #9 of 11 Archive leaderboard report
3D Hand Pose Estimation DexYCB SHO VAUC - #9 of 11 Archive leaderboard report
3D Hand Pose Estimation HO-3D v2 SHO PA-MPJPE (mm) 10.1 #15 of 24 Archive leaderboard report
hand-object pose HO-3D v2 SHO ADD-S - #7 of 9 Archive leaderboard report
hand-object pose HO-3D v2 SHO Average MPJPE (mm) - #7 of 9 Archive leaderboard report
hand-object pose HO-3D v2 SHO OME - #7 of 9 Archive leaderboard report
hand-object pose HO-3D v2 SHO PA-MPJPE 10.1 #7 of 9 Archive leaderboard report
hand-object pose HO-3D v2 SHO ST-MPJPE 31.7 #7 of 9 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.

Methods

Absolute Position EncodingsAdamAttentionBPEDense ConnectionsDropoutLabel SmoothingLayer NormalizationLinear LayerMulti-Head AttentionPosition-Wise Feed-Forward LayerResidual ConnectionSoftmaxTransformer

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