Scene-Level Heterogeneous Physics Simulation with 3D Gaussian Splats
Not on the map. Why?
Abstract (arXiv)
3D Gaussian Splatting (3DGS) has achieved state-of-the-art photorealistic rendering, but the representation gap prevents these assets from being physically interactive. Production-grade physics engines do not understand the 3DGS representation, while prior physics-for-3DGS methods are monolithic silos. These prior works are fundamentally limited, demonstrating only object-centric physics in isolated environments, such as on an ideal plane. They are incapable of interacting with complex static collision geometry or heterogeneous assets. We propose a novel framework that, for the first time, bridges this gap by enabling 3DGS assets to participate in scene-level, heterogeneous, multi-solver physical simulations. Our core contribution is a Representation Abstraction Framework that translates all diverse assets, including 3DGS, virtual meshes, and fluids, into a unified physical particle set. This abstraction is key to enabling complex behaviors, such as the non-rigid deformation of 3DGS assets, within a unified physics pipeline. This particle set, along with the static scene collision boundaries derived from scene capture, is processed within a solver-agnostic physics kernel. The physical results are then mapped back to drive each asset's specific visual reconstruction. This architecture unlocks capabilities impossible with prior art. We demonstrate complex, two-way interactions between deformable 3DGS assets, standard CG assets such as fluids and meshes, and large-scale captured static environments, showcasing realistic coupled phenomena that were previously unattainable.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 21 of its 37 references that are in the map. First posted on arXiv 19 Jun 2026.
Builds on
21 of 37 references.
References · 21
- 20233D Gaussian Splatting for Real-Time Radiance Field Renderingcited by 6,226
- 2021Mip-NeRF 360: Unbounded Anti-Aliased Neural Radiance Fieldscited by 2,032
- 2021Mip-NeRF: A Multiscale Representation for Anti-Aliasing Neural Radiance Fieldscited by 1,964
- 20234D Gaussian Splatting for Real-Time Dynamic Scene Renderingcited by 1,157
- 20242D Gaussian Splatting for Geometrically Accurate Radiance Fieldscited by 1,076
- 2023PhysGaussian: Physics-Integrated 3D Gaussians for Generative Dynamicscited by 377
- 2024PGSR: Planar-based Gaussian Splatting for Efficient and High-Fidelity Surface Reconstructioncited by 285
- 2023DreamGaussian4D: Generative 4D Gaussian Splattingcited by 194
- 2024PhysDreamer: Physics-Based Interaction with 3D Objects via Video Generationcited by 191
- 2024VR-GS: A Physical Dynamics-Aware Interactive Gaussian Splatting System in Virtual Realitycited by 179
- 2023Segment Any 3D Gaussianscited by 161
- 20243D Gaussian as a New Era: A Surveycited by 104
9 more
- 2024GaussianFlow: Splatting Gaussian Dynamics for 4D Content Creationcited by 100
- 2024Physics3D: Learning Physical Properties of 3D Gaussians via Video Diffusioncited by 80
- 20243D Gaussian Splatting: Survey, Technologies, Challenges, and Opportunitiescited by 78
- 20243D Gaussian Splatting in Robotics: A Surveycited by 45
- 2024Gaussian Splashing: Unified Particles for Versatile Motion Synthesis and Renderingcited by 37
- 2024Efficient Physics Simulation for 3D Scenes via MLLM-Guided Gaussian Splattingcited by 32
- 2024GASP: Gaussian Splatting for Physic-Based Simulationscited by 24
- 2025DecoupledGaussian: Object-Scene Decoupling for Physics-Based Interactioncited by 17
- 2024GausSim: Foreseeing Reality by Gaussian Simulator for Elastic Objectscited by 4
Built on by
Not cited yet.