Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

PAD-Hand: Physics-Aware Diffusion for Hand Motion Recovery

About

Significant advancements made in reconstructing hands from images have delivered accurate single-frame estimates, yet they often lack physics consistency and provide no notion of how confidently the motion satisfies physics. In this paper, we propose a novel physics-aware conditional diffusion framework that refines noisy pose sequences into physically plausible hand motion while estimating the physics variance in motion estimates. Building on a MeshCNN-Transformer backbone, we formulate Euler-Lagrange dynamics for articulated hands. Unlike prior works that enforce zero residuals, we treat the resulting dynamic residuals as virtual observables to more effectively integrate physics. Through a last-layer Laplace approximation, our method produces per-joint, per-time variances that measure physics consistency and offers interpretable variance maps indicating where physical consistency weakens. Experiments on two well-known hand datasets show consistent gains over strong image-based initializations and competitive video-based methods. Qualitative results confirm that our variance estimations are aligned with the physical plausibility of the motion in image-based estimates.

Elkhan Ismayilzada, Yufei Zhang, Zijun Cui• 2026

Related benchmarks

TaskDatasetResultRank
3D Hand ReconstructionDexYCB (official evaluation)
MPJPE10.56
8
3D Hand ReconstructionHO3D (official evaluation)
PA-MPJPE7.43
7
Hand Motion RecoveryHO3D
PA-MPJPE7.43
3
Hand Motion RecoveryDexYCB
PA-MPJPE4.63
3
Hand Pose EstimationTACO S1 (test)
PA-MPJPE8.02
3
Showing 5 of 5 rows

Other info

Follow for update