English

InterPhys: Physics-aware Human Motion Synthesis in a Dynamic Scene

Computer Vision and Pattern Recognition 2026-05-05 v1

Abstract

This paper tackles the problem of physics-aware human motion synthesis in a dynamic scene. Unlike existing works which mainly tend to generate physically unrealistic motions due to limited contact modeling, typically restricted to hands, in this paper, we introduce a physics-aware human motion generation framework that explicitly models the full spectrum of human-related forces, including human-object, human-scene, and internal body dynamics.~Our method imposes soft physical constraints to maintain force and torque balance, ensuring physically grounded motion synthesis. We further propose a novel continuous distance-based force model that generalizes contact modeling to arbitrary surfaces, capturing interactions not only with static environments but also with dynamic, moving objects. Extensive experiments show that our approach significantly improves physical plausibility and generalizes well to complex scenes, setting a new benchmark for physically consistent human motion generation.

Keywords

Cite

@article{arxiv.2605.01036,
  title  = {InterPhys: Physics-aware Human Motion Synthesis in a Dynamic Scene},
  author = {Chaoyue Xing and Wei Mao and Miaomiao Liu},
  journal= {arXiv preprint arXiv:2605.01036},
  year   = {2026}
}

Comments

Accepted to CVPR2026

R2 v1 2026-07-01T12:45:52.545Z