PhyGenHOI: Physically-Aware 4D Generation of Dynamic Human-Object Interactions

Omer Benishu, Gal Fiebelman, Sagie Benaim

arXiv:2605.30268 · 2026-05-30 공개 · arXiv · PDF

motion-generation human-object-interaction material-point-method physical-simulation video-sds contact-driven-simulation semantic-agent motion-diffusion-model

Abstract

We address the task of generating physically accurate and visually faithful 4D Human-Object Interaction (HOI). Given a static 3D human and target object represented as 3D Gaussian Splats (3DGS), our goal is to synthesize dynamic scenes where the human actively engages with the object through actions, such as punching or kicking, in accordance with a given input text. To this end, we introduce PhyGenHOI, a novel framework that couples generative human motion with an explicit physical object simulation. We model the human as a semantic agent driven by a Motion Diffusion Model (MDM) and the object as a physical agent simulated via the Material Point Method (MPM), utilizing 3D Gaussians as a unified, differentiable representation. We supervise their interaction through three coupled mechanisms: (1) A Windowed Attraction Loss that temporally synchronizes generative motion to intercept the object; (2) A Contact-Driven Re-simulation step that triggers physically consistent momentum transfer upon impact; and (3) A Masked Video-SDS objective that injects video-based priors to enhance contact fidelity. Experiments show PhyGenHOI generates physically consistent 4D HOI across diverse actions, humans, and objects, outperforming baselines. Project page and videos: https://omerbenishu.github.io/PhyGenHOI/

한국어 요약

📋 한 줄 요약

**[4D HOI 생성 / 물리 시뮬레이션]** PhyGenHOI가 3DGS 인간·물체의 동적 상호작용을 MDM 의미 에이전트와 MPM 물리 에이전트로 결합, Windowed Attraction Loss·Contact-Driven Re-simulation·Masked Video-SDS 3 메커니즘으로 물리 일관 4D HOI 생성.

🎯 핵심 기여도

💡 핵심 아이디어

물리 정확·시각 충실 4D HOI는 generative 인간 모션과 explicit 물리 시뮬레이션의 단순 cascade가 아닌, 3D Gaussian을 공통 differentiable 표현으로 두고 attraction·re-simulation·video-SDS 3 coupling으로 두 에이전트를 동기화해야 달성된다.

🔬 기술적 접근법

📊 주요 결과

💭 의의 및 한계

**의의**: 4D HOI에 explicit 물리 시뮬레이션을 통합하는 새 패러다임, 3DGS의 differentiable 표현으로 generative·시뮬레이션 결합, 충돌·momentum transfer의 명시적 모델링으로 시각만으로 어려운 물리 효과 재현. **한계**: MPM 시뮬레이션의 계산 비용, 펀치·킥류 강한 contact 외 미세 조작·도구 사용은 추가 검증, MDM·MPM 두 에이전트 간 hyperparameter 조정 부담.

🚀 실용적 활용