English

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

Computer Vision and Pattern Recognition 2026-03-31 v2

Abstract

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.

Keywords

Cite

@article{arxiv.2603.26068,
  title  = {PAD-Hand: Physics-Aware Diffusion for Hand Motion Recovery},
  author = {Elkhan Ismayilzada and Yufei Zhang and Zijun Cui},
  journal= {arXiv preprint arXiv:2603.26068},
  year   = {2026}
}

Comments

Accepted to CVPR 2026

R2 v1 2026-07-01T11:40:12.947Z