PhysiInter: Integrating Physical Mapping for High-Fidelity Human Interaction Generation

TL;DR

PhysiInter enhances human motion generation by integrating physical constraints through a novel mapping process, significantly improving realism and physical fidelity in multi-person interactions using physics-based simulation and specialized loss functions.

Contribution

The paper introduces a physical mapping approach for motion synthesis, incorporating physics-based simulation and new loss functions to improve motion realism and physical validity in multi-person scenarios.

Findings

3%-89% improvement in physical fidelity

Effective motion adjustment within physics-based environment

Enhanced multi-person interaction realism

Abstract

Driven by advancements in motion capture and generative artificial intelligence, leveraging large-scale MoCap datasets to train generative models for synthesizing diverse, realistic human motions has become a promising research direction. However, existing motion-capture techniques and generative models often neglect physical constraints, leading to artifacts such as interpenetration, sliding, and floating. These issues are exacerbated in multi-person motion generation, where complex interactions are involved. To address these limitations, we introduce physical mapping, integrated throughout the human interaction generation pipeline. Specifically, motion imitation within a physics-based simulation environment is used to project target motions into a physically valid space. The resulting motions are adjusted to adhere to real-world physics constraints while retaining their original semantic meaning. This mapping not only improves MoCap data quality but also directly informs post-processing of generated motions. Given the unique interactivity of multi-person scenarios, we propose a tailored motion representation framework. Motion Consistency (MC) and Marker-based Interaction (MI) loss functions are introduced to improve model performance. Experiments show our method achieves impressive results in generated human motion quality, with a 3%-89% improvement in physical fidelity. Project page http://yw0208.github.io/physiinter