Saved in:
Bibliographic Details
Main Authors: Lei, Nan, Li, Yuan-Ming, Zeng, Ling-An, Xu, Liang, Xia, Zhi-Wei, Huang, Hui-Wen, Hong, Fa-Ting, Zheng, Wei-Shi
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2605.00517
Tags: Add Tag
No Tags, Be the first to tag this record!
Table of Contents:
  • Despite substantial progress in text-driven 3D human motion synthesis, generating realistic multi-person interaction sequences remains challenging. Notably, body inter-penetration is a pervasive issue from both data acquisition to the generated results, which significantly undermines the realism and usability. Previous generative models either ignored this issue or introduced computationally expensive mesh-level loss functions to alleviate inter-body collisions. In this paper, we propose a general-purpose and computationally efficient optimization strategy named PhysiGen to explicitly integrate collision-aware physical constraints for human-human interaction generation. Specifically, we simplify the high-resolution human body mesh into geometric primitives to greatly reduce the cost of inter-person collision detection. Moreover, we identify the collision regions as the guidance of the optimization directions. PhysiGen is plug-and-play and can be readily integrated into existing human interaction generation models. Extensive cross-dataset and cross-model experiments show that our method can effectively reduce interpenetration and significantly improve visual coherence and physical plausibility compared to the state-of-the-art methods.