Gaussian-Augmented Physics Simulation and System Identification with Complex Colliders
By: Federico Vasile , Ri-Zhao Qiu , Lorenzo Natale and more
Potential Business Impact:
Lets robots understand and interact with real objects.
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.
Similar Papers
A Convex Formulation of Material Points and Rigid Bodies with GPU-Accelerated Async-Coupling for Interactive Simulation
Robotics
Simulates robots and soft things much faster.
PhysMorph-GS: Differentiable Shape Morphing via Joint Optimization of Physics and Rendering Objectives
Graphics
Makes computer shapes move and change realistically.
Differentiable Material Point Method for the Control of Deformable Objects
Robotics
Makes robots quickly stop wiggling ropes.