Papers › Learning joint reconstruction of hands and manipulated objects

Learning joint reconstruction of hands and manipulated objects

11 Apr 2019CVPR 2019 6arXiv:1904.05767archive 2025-07-28

Yana Hasson, Gül Varol, Dimitrios Tzionas, Igor Kalevatykh, Michael J. Black, Ivan Laptev, Cordelia Schmid

Estimating hand-object manipulations is essential for interpreting and imitating human actions. Previous work has made significant progress towards reconstruction of hand poses and object shapes in isolation. Yet, reconstructing hands and objects during manipulation is a more challenging task due to significant occlusions of both the hand and object. While presenting challenges, manipulations may also simplify the problem since the physics of contact restricts the space of valid hand-object configurations. For example, during manipulation, the hand and object should be in contact but not interpenetrate. In this work, we regularize the joint reconstruction of hands and objects with manipulation constraints. We present an end-to-end learnable model that exploits a novel contact loss that favors physically plausible hand-object constellations. Our approach improves grasp quality metrics over baselines, using RGB images as input. To train and evaluate the model, we also propose a new large-scale synthetic dataset, ObMan, with hand-object manipulations. We demonstrate the transferability of ObMan-trained models to real data.

PaperPDFConference PDFCode

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

Code

hassony2/manopth pytorchGPL-3.0 report
hassony2/obman_train pytorchGPL-3.0 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 Joint ReconstructionObjecthand-object pose

1 archive task tag without a task page not shown.

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
3D Hand Pose Estimation FreiHAND Hasson et al. PA-F@15mm 0.908 #33 of 33 Archive leaderboard report
3D Hand Pose Estimation FreiHAND Hasson et al. PA-F@5mm 0.436 #33 of 33 Archive leaderboard report
3D Hand Pose Estimation FreiHAND Hasson et al. PA-MPVPE 13.2 #33 of 33 Archive leaderboard report
hand-object pose DexYCB HMO ADD-S - #7 of 9 Archive leaderboard report
hand-object pose DexYCB HMO Average MPJPE (mm) 17.6 #7 of 9 Archive leaderboard report
hand-object pose DexYCB HMO MCE - #7 of 9 Archive leaderboard report
hand-object pose DexYCB HMO OCE - #7 of 9 Archive leaderboard report
hand-object pose DexYCB HMO Procrustes-Aligned MPJPE - #7 of 9 Archive leaderboard report
hand-object pose HO-3D v2 HMO ADD-S - #8 of 9 Archive leaderboard report
hand-object pose HO-3D v2 HMO Average MPJPE (mm) - #8 of 9 Archive leaderboard report
hand-object pose HO-3D v2 HMO OME - #8 of 9 Archive leaderboard report
hand-object pose HO-3D v2 HMO PA-MPJPE 11.0 #8 of 9 Archive leaderboard report
hand-object pose HO-3D v2 HMO ST-MPJPE 31.8 #8 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.

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