Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2511.06846 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866908640509689856 |
|---|---|
| author | Vasile, Federico Qiu, Ri-Zhao Natale, Lorenzo Wang, Xiaolong |
| author_facet | Vasile, Federico Qiu, Ri-Zhao Natale, Lorenzo Wang, Xiaolong |
| contents | System identification involving the geometry, appearance, and physical properties from video observations is a challenging task with applications in robotics and graphics. Recent approaches have relied on fully differentiable Material Point Method (MPM) and rendering for simultaneous optimization of these properties. However, they are limited to simplified object-environment interactions with planar colliders and fail in more challenging scenarios where objects collide with non-planar surfaces. We propose AS-DiffMPM, a differentiable MPM framework that enables physical property estimation with arbitrarily shaped colliders. Our approach extends existing methods by incorporating a differentiable collision handling mechanism, allowing the target object to interact with complex rigid bodies while maintaining end-to-end optimization. We show AS-DiffMPM can be easily interfaced with various novel view synthesis methods as a framework for system identification from visual observations. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2511_06846 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Gaussian-Augmented Physics Simulation and System Identification with Complex Colliders Vasile, Federico Qiu, Ri-Zhao Natale, Lorenzo Wang, Xiaolong Computer Vision and Pattern Recognition System identification involving the geometry, appearance, and physical properties from video observations is a challenging task with applications in robotics and graphics. Recent approaches have relied on fully differentiable Material Point Method (MPM) and rendering for simultaneous optimization of these properties. However, they are limited to simplified object-environment interactions with planar colliders and fail in more challenging scenarios where objects collide with non-planar surfaces. We propose AS-DiffMPM, a differentiable MPM framework that enables physical property estimation with arbitrarily shaped colliders. Our approach extends existing methods by incorporating a differentiable collision handling mechanism, allowing the target object to interact with complex rigid bodies while maintaining end-to-end optimization. We show AS-DiffMPM can be easily interfaced with various novel view synthesis methods as a framework for system identification from visual observations. |
| title | Gaussian-Augmented Physics Simulation and System Identification with Complex Colliders |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2511.06846 |