Papers › A Probabilistic Attention Model with Occlusion-aware Texture Regression for 3D Hand...

A Probabilistic Attention Model with Occlusion-aware Texture Regression for 3D Hand Reconstruction from a Single RGB Image

27 Apr 2023CVPR 2023 1arXiv:2304.14299archive 2025-07-28

Zheheng Jiang, Hossein Rahmani, Sue Black, Bryan M. Williams

Recently, deep learning based approaches have shown promising results in 3D hand reconstruction from a single RGB image. These approaches can be roughly divided into model-based approaches, which are heavily dependent on the model's parameter space, and model-free approaches, which require large numbers of 3D ground truths to reduce depth ambiguity and struggle in weakly-supervised scenarios. To overcome these issues, we propose a novel probabilistic model to achieve the robustness of model-based approaches and reduced dependence on the model's parameter space of model-free approaches. The proposed probabilistic model incorporates a model-based network as a prior-net to estimate the prior probability distribution of joints and vertices. An Attention-based Mesh Vertices Uncertainty Regression (AMVUR) model is proposed to capture dependencies among vertices and the correlation between joints and mesh vertices to improve their feature representation. We further propose a learning based occlusion-aware Hand Texture Regression model to achieve high-fidelity texture reconstruction. We demonstrate the flexibility of the proposed probabilistic model to be trained in both supervised and weakly-supervised scenarios. The experimental results demonstrate our probabilistic model's state-of-the-art accuracy in 3D hand and texture reconstruction from a single image in both training schemes, including in the presence of severe occlusions.

PaperPDFConference PDFCode

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

Code

zhehengjianglancaster/amvur officialmentioned in paperpytorch 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 Estimationregression

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
3D Hand Pose Estimation FreiHAND AMVUR PA-F@15mm 0.987 #12 of 33 Archive leaderboard report
3D Hand Pose Estimation FreiHAND AMVUR PA-F@5mm 0.767 #12 of 33 Archive leaderboard report
3D Hand Pose Estimation FreiHAND AMVUR PA-MPJPE 6.2 #12 of 33 Archive leaderboard report
3D Hand Pose Estimation FreiHAND AMVUR PA-MPVPE 6.1 #12 of 33 Archive leaderboard report
3D Hand Pose Estimation HO-3D v2 AMVUR AUC_J 0.835 #6 of 24 Archive leaderboard report
3D Hand Pose Estimation HO-3D v2 AMVUR AUC_V 0.836 #6 of 24 Archive leaderboard report
3D Hand Pose Estimation HO-3D v2 AMVUR F@15mm 0.965 #6 of 24 Archive leaderboard report
3D Hand Pose Estimation HO-3D v2 AMVUR F@5mm 0.608 #6 of 24 Archive leaderboard report
3D Hand Pose Estimation HO-3D v2 AMVUR PA-MPJPE (mm) 8.3 #6 of 24 Archive leaderboard report
3D Hand Pose Estimation HO-3D v2 AMVUR PA-MPVPE 8.2 #6 of 24 Archive leaderboard report
3D Hand Pose Estimation HO-3D v3 AMVUR AUC_J 0.826 #3 of 8 Archive leaderboard report
3D Hand Pose Estimation HO-3D v3 AMVUR AUC_V 0.834 #3 of 8 Archive leaderboard report
3D Hand Pose Estimation HO-3D v3 AMVUR F@15mm 0.964 #3 of 8 Archive leaderboard report
3D Hand Pose Estimation HO-3D v3 AMVUR F@5mm 0.593 #3 of 8 Archive leaderboard report
3D Hand Pose Estimation HO-3D v3 AMVUR PA-MPJPE 8.7 #3 of 8 Archive leaderboard report
3D Hand Pose Estimation HO-3D v3 AMVUR PA-MPVPE 8.3 #3 of 8 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