Guardado en:
Detalles Bibliográficos
Autores principales: Lei, Nan, Li, Yuan-Ming, Zeng, Ling-An, Xu, Liang, Xia, Zhi-Wei, Huang, Hui-Wen, Hong, Fa-Ting, Zheng, Wei-Shi
Formato: Preprint
Publicado: 2026
Materias:
Acceso en línea:https://arxiv.org/abs/2605.00517
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866911638560440320
author Lei, Nan
Li, Yuan-Ming
Zeng, Ling-An
Xu, Liang
Xia, Zhi-Wei
Huang, Hui-Wen
Hong, Fa-Ting
Zheng, Wei-Shi
author_facet Lei, Nan
Li, Yuan-Ming
Zeng, Ling-An
Xu, Liang
Xia, Zhi-Wei
Huang, Hui-Wen
Hong, Fa-Ting
Zheng, Wei-Shi
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.
format Preprint
id arxiv_https___arxiv_org_abs_2605_00517
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle PhysiGen: Integrating Collision-Aware Physical Constraints for High-Fidelity Human-Human Interaction Generation
Lei, Nan
Li, Yuan-Ming
Zeng, Ling-An
Xu, Liang
Xia, Zhi-Wei
Huang, Hui-Wen
Hong, Fa-Ting
Zheng, Wei-Shi
Computer Vision and Pattern Recognition
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.
title PhysiGen: Integrating Collision-Aware Physical Constraints for High-Fidelity Human-Human Interaction Generation
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2605.00517