Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2602.17117 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917281756348416 |
|---|---|
| author | Cao, Yicheng Huang, Zhuo Yao, Yu Ying, Yiming Dong, Daoyi Liu, Tongliang |
| author_facet | Cao, Yicheng Huang, Zhuo Yao, Yu Ying, Yiming Dong, Daoyi Liu, Tongliang |
| contents | Physical simulation predicts future states of objects based on material properties and external loads, enabling blueprints for both Industry and Engineering to conduct risk management. Current 3D reconstruction-based simulators typically rely on explicit, step-wise updates, which are sensitive to step time and suffer from rapid accuracy degradation under complicated scenarios, such as high-stiffness materials or quasi-static movement. To address this, we introduce i-PhysGaussian, a framework that couples 3D Gaussian Splatting (3DGS) with an implicit Material Point Method (MPM) integrator. Unlike explicit methods, our solution obtains an end-of-step state by minimizing a momentum-balance residual through implicit Newton-type optimization with a GMRES solver. This formulation significantly reduces time-step sensitivity and ensures physical consistency. Our results demonstrate that i-PhysGaussian maintains stability at up to 20x larger time steps than explicit baselines, preserving structural coherence and smooth motion even in complex dynamic transitions. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_17117 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | i-PhysGaussian: Implicit Physical Simulation for 3D Gaussian Splatting Cao, Yicheng Huang, Zhuo Yao, Yu Ying, Yiming Dong, Daoyi Liu, Tongliang Machine Learning Physical simulation predicts future states of objects based on material properties and external loads, enabling blueprints for both Industry and Engineering to conduct risk management. Current 3D reconstruction-based simulators typically rely on explicit, step-wise updates, which are sensitive to step time and suffer from rapid accuracy degradation under complicated scenarios, such as high-stiffness materials or quasi-static movement. To address this, we introduce i-PhysGaussian, a framework that couples 3D Gaussian Splatting (3DGS) with an implicit Material Point Method (MPM) integrator. Unlike explicit methods, our solution obtains an end-of-step state by minimizing a momentum-balance residual through implicit Newton-type optimization with a GMRES solver. This formulation significantly reduces time-step sensitivity and ensures physical consistency. Our results demonstrate that i-PhysGaussian maintains stability at up to 20x larger time steps than explicit baselines, preserving structural coherence and smooth motion even in complex dynamic transitions. |
| title | i-PhysGaussian: Implicit Physical Simulation for 3D Gaussian Splatting |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2602.17117 |