PhysiGen: Integrating Collision-Aware Physical Constraints for High-Fidelity Human-Human Interaction Generation

TL;DR

PhysiGen introduces an efficient optimization method that incorporates collision-aware physical constraints to enhance the realism and physical plausibility of multi-person interaction generation.

Contribution

It presents a novel, computationally efficient approach that simplifies collision detection and can be integrated into existing models to improve interaction realism.

Findings

Reduces inter-penetration in generated interactions

Improves visual coherence and physical plausibility

Effective across multiple datasets and models

Abstract

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.