MonoPhysics: Estimating Geometry, Appearance, and Physical Parameters from Monocular Videos
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866914614631989248 |
|---|---|
| author | Rho, Daniel Choi, Jun Myeong Thornton, Matthew Dey, Biswadip Sengupta, Roni |
| author_facet | Rho, Daniel Choi, Jun Myeong Thornton, Matthew Dey, Biswadip Sengupta, Roni |
| contents | Existing inverse physics methods recover physical parameters from multi-view videos, where geometric constraints across views resolve scale and 3D structure. In monocular settings, however, such constraints are absent, leading to severe scale ambiguity, inaccurate geometry, and weak coupling between appearance optimization and physical simulation. We propose MonoPhysics, a framework for monocular inverse physics estimation of deformable objects using differentiable MPM simulation and 3D Gaussian Splatting, which jointly optimizes geometry, appearance, and physical parameters from a single camera view. We address these challenges through three visual-physical bridges: global scale alignment, physics-aware geometry refinement, and a differentiable position map, which together enable accurate optimization from monocular observations alone. We evaluate on Vid2Sim and our new dataset of elastic and plastic objects, showing that MonoPhysics outperforms existing baselines in monocular settings and achieves performance comparable to multi-view baselines using only a single camera. Our project page is available at https://daniel03c1.github.io/MonoPhysics/ |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_30320 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | MonoPhysics: Estimating Geometry, Appearance, and Physical Parameters from Monocular Videos Rho, Daniel Choi, Jun Myeong Thornton, Matthew Dey, Biswadip Sengupta, Roni Computer Vision and Pattern Recognition Existing inverse physics methods recover physical parameters from multi-view videos, where geometric constraints across views resolve scale and 3D structure. In monocular settings, however, such constraints are absent, leading to severe scale ambiguity, inaccurate geometry, and weak coupling between appearance optimization and physical simulation. We propose MonoPhysics, a framework for monocular inverse physics estimation of deformable objects using differentiable MPM simulation and 3D Gaussian Splatting, which jointly optimizes geometry, appearance, and physical parameters from a single camera view. We address these challenges through three visual-physical bridges: global scale alignment, physics-aware geometry refinement, and a differentiable position map, which together enable accurate optimization from monocular observations alone. We evaluate on Vid2Sim and our new dataset of elastic and plastic objects, showing that MonoPhysics outperforms existing baselines in monocular settings and achieves performance comparable to multi-view baselines using only a single camera. Our project page is available at https://daniel03c1.github.io/MonoPhysics/ |
| title | MonoPhysics: Estimating Geometry, Appearance, and Physical Parameters from Monocular Videos |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2605.30320 |