PoseShield: Neural Collision Fields for Human Self-Collision Resolution
Self-collision remains a persistent challenge in SMPL-based human pose estimation and motion generation. Under extreme articulations or stochastic motion synthesis, generated meshes frequently exhibit self-penetrations, leading to physically implausible results. We propose PoseShield, a neural collision constraint defined directly in SMPL pose space. We formulate collision correction as a constrained optimization problem and connect the learned constraint with the Eikonal equation. Enforcing Eikonal regularization ensures non-vanishing gradients near the collision boundary, improving numerical stability and robustness of the optimization process. Unlike prior methods that operate in the m...
| Authors | Zhengyuan Li, Zeyun Deng, Yifan Shen et al. |
|---|---|
| Primary category | cs.CV |
| Published | 29 June 2026 |
| Last updated at source | 28 August 2026 |
Models and datasets referencing this paper
- ZYYY99/Humans_with_CollisionDataset
Silytics shows public metadata from arXiv and links to the original. Information may be incomplete or out of date. Last refreshed 17 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.