Research map / Video / Video generation
PAD-Hand: Physics-Aware Diffusion for Hand Motion Recovery
Elkhan Ismayilzada, Yufei Zhang, Zijun Cui
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| refine WiLoR estimates with PAD-Hand diffusion | WiLoR · DexYCB | ACCEL (mm/frame^2): 6.70 -> 3.34 | Improved |
| refine WiLoR estimates with PAD-Hand diffusion | WiLoR · DexYCB | MPJPE (mm): 12.75 -> 10.56 | Improved |
| refine WiLoR estimates with PAD-Hand diffusion | WiLoR · HO3D | PA-MPJPE (mm): 7.50 -> 7.43 | No clear effect |
| refine WiLoR estimates with PAD-Hand diffusion | WiLoR · HO3D | ACCEL (mm/frame^2): 4.98 -> 2.71 | Improved |
| add Euler-Lagrange residual loss to data loss (ablation) | PAD-Hand · DexYCB | MPJPE (mm): 10.62 -> 10.56 | Improved |
| add Euler-Lagrange residual loss to data loss (ablation) | PAD-Hand · DexYCB | ACCEL (mm/frame^2): 3.36 -> 3.34 | Improved |
| use probabilistic virtual-observable physics instead of deterministic residual penalty (ablation) | PAD-Hand · DexYCB | MPJPE (mm): 10.61 -> 10.56 | Improved |
| use probabilistic virtual-observable physics instead of deterministic residual penalty (ablation) | PAD-Hand · DexYCB | PA-MPJPE (mm): 4.66 -> 4.63 | Improved |
| use WiLoR + PAD-Hand instead of MaskHand | DexYCB hand reconstruction · DexYCB | MPJPE (mm): 11.70 -> 10.56 | Improved |
Closest papers by meaning
- The Surprising Effectiveness of Video Diffusion Models for Hand Motion Reconstruction (NeurIPS 2026 · similarity 0.89)
- ComPose: When to Trust Hands for Object Pose Tracking (NeurIPS 2026 · similarity 0.89)
- Physics-Aware Hand-Object Interaction Denoising (CVPR 2024 · similarity 0.89)
- StableHand: Quality-Aware Flow Matching for World-Space Dual-Hand Motion Estimation from Egocentric Video (NeurIPS 2026 · similarity 0.89)
- CoDA: Coordinated Diffusion Noise Optimization for Whole-Body Manipulation of Articulated Objects (NeurIPS 2025 · similarity 0.88)
- FoundHand: Large-Scale Domain-Specific Learning for Controllable Hand Image Generation (CVPR 2025 · similarity 0.87)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
