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

2026-05-01

AI Summary

Existing approaches to human motion generation often suffer from physically implausible results due to contact modeling limited to the hands. This work proposes a physics-aware framework that explicitly models the full spectrum of contacts—including interactions between the body and objects, scenes, and self-limb collisions—through a continuous distance-driven force model. By integrating soft physical constraints with force and torque balance mechanisms, the method synthesizes multi-body dynamics-consistent motions. It supports arbitrary surface interactions with both static environments and dynamic objects, significantly enhancing the physical plausibility of generated actions. The approach demonstrates strong generalization in complex, dynamic scenarios and establishes a new benchmark for physically consistent human motion generation.

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.

Problem

• physics-aware
• human motion synthesis
• dynamic scene
• contact modeling
• physical plausibility

Innovation

• physics-aware motion synthesis
• full-body contact modeling
• force and torque balance
• continuous distance-based force model
• dynamic scene interaction