PhysGraph: Physics-Based Integration Using Graph Neural Networks

TL;DR

PhysGraph introduces a graph neural network-based method that learns to predict physical system responses to forces, enabling mesh-independent, generalizable simulations including unseen external forces like collisions.

Contribution

The paper proposes a novel physics simulation approach that separates force evaluation from integration, allowing for a generalizable, mesh-independent neural integrator trained on simple force data.

Findings

The model generalizes across different mesh types and resolutions.

It effectively predicts responses to unseen external forces like collisions.

The approach enhances detail in coarse clothing geometries for virtual applications.

Abstract

Physics-based simulation of mesh based domains remains a challenging task. State-of-the-art techniques can produce realistic results but require expert knowledge. A major bottleneck in many approaches is the step of integrating a potential energy in order to compute velocities or displacements. Recently, learning based method for physics-based simulation have sparked interest with graph based approaches being a promising research direction. One of the challenges for these methods is to generate models that are mesh independent and generalize to different material properties. Moreover, the model should also be able to react to unforeseen external forces like ubiquitous collisions. Our contribution is based on a simple observation: evaluating forces is computationally relatively cheap for traditional simulation methods and can be computed in parallel in contrast to their integration. If we learn how a system reacts to forces in general, irrespective of their origin, we can learn an integrator that can predict state changes due to the total forces with high generalization power. We effectively factor out the physical model behind resulting forces by relying on an opaque force module. We demonstrate that this idea leads to a learnable module that can be trained on basic internal forces of small mesh patches and generalizes to different mesh typologies, resolutions, material parameters and unseen forces like collisions at inference time. Our proposed paradigm is general and can be used to model a variety of physical phenomena. We focus our exposition on the detail enhancement of coarse clothing geometry which has many applications including computer games, virtual reality and virtual try-on.