Search papers, labs, and topics across Lattice.
MonoPhysics tackles the problem of inverse physics estimation from monocular videos of deformable objects by jointly optimizing geometry, appearance, and physical parameters. It leverages differentiable Material Point Method (MPM) simulation and 3D Gaussian Splatting, introducing three key components: global scale alignment, physics-aware geometry refinement, and a differentiable position map. Experiments on Vid2Sim and a new dataset demonstrate that MonoPhysics achieves performance comparable to multi-view methods using only monocular input, outperforming existing monocular baselines.
Monocular videos, previously insufficient for accurate inverse physics, can now yield results rivaling multi-view methods thanks to a novel visual-physical bridging framework.
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/
