PoseShield: Neural Collision Fields for Human Self-Collision Resolution
For researchers and practitioners working with SMPL-based human models, this provides a generator-agnostic post-hoc collision corrector that improves physical plausibility without retraining motion models.
PoseShield addresses self-collision in SMPL-based human pose estimation and motion generation by learning a neural collision constraint in pose space, achieving a 95.8% success rate on a new benchmark, outperforming prior methods.
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 mesh space or rely on heuristic penalties, our approach operates directly in the low-dimensional space of human poses and is theoretically grounded. The same learned constraint extends to human motion sequences, providing a generator-agnostic post-hoc collision corrector without retraining the underlying motion model. Experiments on a newly constructed SMPL pose benchmark show that our method achieves a 95.8% success rate and outperforms state-of-the-art baselines.