Half-Physics: Enabling Kinematic 3D Human Model with Physical Interactions

Arxiv 2025

Li Siyao1,2*, Yao Feng3, Omid Taheri1, Chen Change Loy2, Michael J. Black1
1Max Planck Institute for Intelligent Systems 2 S-Lab, Nanyang Technological University 3 Stanford
  • *work done during internship at MPI-IS
Teaser GIF

Half Physics enables kinematical SMPL-X plysically interact with the environment

Abstract

While current general-purpose 3D human models (e.g., SMPL-X) efficiently represent accurate human shape and pose, they lacks the ability to physically interact with the environment due to the kinematic nature. As a result, kinematic-based interaction models often suffer from issues such as interpenetration and unrealistic object dynamics. To address this limitation, we introduce a novel approach that embeds SMPL-X into a tangible entity capable of dynamic physical interactions with its surroundings. Specifically, we propose a “half-physics” mechanism that transforms 3D kinematic motion into a physics simulation. Our approach maintains kinematic control over inherent SMPL-X poses while ensuring physically plausible interactions with scenes and objects, effectively eliminating penetration and unrealistic object dynamics. Unlike reinforcement learning-based methods, which demand extensive and complex training, our half-physics method is learning-free and generalizes to any body shape and motion; meanwhile, it operates in real time. Moreover, it preserves the fidelity of the original kinematic motion while seamlessly integrating physical interactions.

Video

Human-Scene Interaction

Teaser GIF
Teaser GIF
Teaser GIF

Human-Object Interaction

Teaser GIF Teaser GIF
Teaser GIF Teaser GIF

Physical Factor Augmentation

Teaser GIF
Teaser GIF
Teaser GIF

Controllable Passive Joint Stiffness Compensition

Teaser GIF

BibTeX

@article{siyao2025half,
      title   = {Half-Physics: Enabling Kinematic 3D Human Model with Physical Interactions},
      author  = {Siyao, Li and Feng, Yao and Tehari, Omid and Loy, Chen Change and Black, Michael J},
      journal = {arXiv preprint arXiv:2507.23778},
      year    = {2025}  
}

License

Code is released under MIT License.