DecoupledGaussian: Object-Scene Decoupling for Physics-Based Interaction

Miaowei Wang1, Yibo Zhang2, Rui Ma2, Weiwei Xu3, Changqing Zou3, Daniel Morris4,
1The University of Edinburgh, 2Jilin University, 3Zhejiang University, 4Michigan State University
CVPR2025 Accepted
arXiv Code

DecoupledGaussian decomposes static objects and contacted scenes from videos or multi-view images, enabling various simulations

Abstract

We present DecoupledGaussian, a novel system that decouples static objects from their contacted surfaces captured in-the-wild videos, a key prerequisite for realistic Newtonian-based physical simulations. Unlike prior methods focused on synthetic data or elastic jittering along the contact surface, which prevent objects from fully detaching or moving independently, DecoupledGaussian allows for significant positional changes without being constrained by the initial contacted surface. Recognizing the limitations of current 2D inpainting tools for restoring 3D locations, our approach proposes joint Poisson fields to repair and expand the Gaussians of both objects and contacted scenes after separation. This is complemented by a multi-carve strategy to refine the object's geometry. Our system enables realistic simulations of decoupling motions, collisions, and fractures driven by user-specified impulses, supporting complex interactions within and across multiple scenes. We validate DecoupledGaussian through a comprehensive user study and quantitative benchmarks. This system enhances digital interaction with objects and scenes in real-world environments, benefiting industries such as VR, robotics, and autonomous driving.

Pipeline

DecoupledGaussian is an interactive simulation system that enables objects to detach from their initial contact surfaces after applying our proposed restoration pipeline, driven by user-specified impulses (red arrow on the right).

BibTeX

@misc{wang2025decoupledgaussianobjectscenedecouplingphysicsbased,
        title={DecoupledGaussian: Object-Scene Decoupling for Physics-Based Interaction}, 
        author={Miaowei Wang and Yibo Zhang and Rui Ma and Weiwei Xu and Changqing Zou and Daniel Morris},
        year={2025},
        eprint={2503.05484},
        archivePrefix={arXiv},
        primaryClass={cs.GR},
        url={https://arxiv.org/abs/2503.05484}, 
  }