# PhysGraph: Physics-Based Integration Using Graph Neural Networks

arXiv: https://arxiv.org/abs/2301.11841 · HTML: https://mlsanity.com/paper/2301.11841/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 44 references that are in the map.
- First posted on arXiv 27 Jan 2023.

## Builds on (most cited first, 23 of 23)

- [Relational inductive biases, deep learning, and graph networks](https://mlsanity.com/paper/1806.01261/) (2018)
- [AMASS: Archive of Motion Capture as Surface Shapes](https://mlsanity.com/paper/1904.03278/) (2019)
- [Learning to Simulate Complex Physics with Graph Networks](https://mlsanity.com/paper/2002.09405/) (2020)
- [Learning Mesh-Based Simulation with Graph Networks](https://mlsanity.com/paper/2010.03409/) (2020)
- [Learning Particle Dynamics for Manipulating Rigid Bodies, Deformable Objects, and Fluids](https://mlsanity.com/paper/1810.01566/) (2018)
- [Deep Learning Methods for Reynolds-Averaged Navier-Stokes Simulations of Airfoil Flows](https://mlsanity.com/paper/1810.08217/) (2018)
- [TailorNet: Predicting Clothing in 3D as a Function of Human Pose, Shape and Garment Style](https://mlsanity.com/paper/2003.04583/) (2020)
- [MultiScale MeshGraphNets](https://mlsanity.com/paper/2210.00612/) (2022)
- [DeepWrinkles: Accurate and Realistic Clothing Modeling](https://mlsanity.com/paper/1808.03417/) (2018)
- [Learning-Based Animation of Clothing for Virtual Try-On](https://mlsanity.com/paper/1903.07190/) (2019)
- [SNUG: Self-Supervised Neural Dynamic Garments](https://mlsanity.com/paper/2204.02219/) (2022)
- [Self-Supervised Collision Handling via Generative 3D Garment Models for Virtual Try-On](https://mlsanity.com/paper/2105.06462/) (2021)
- [HOOD: Hierarchical Graphs for Generalized Modelling of Clothing Dynamics](https://mlsanity.com/paper/2212.07242/) (2022)
- [PBNS: Physically Based Neural Simulator for Unsupervised Garment Pose Space Deformation](https://mlsanity.com/paper/2012.11310/) (2020)
- [Neural Subdivision](https://mlsanity.com/paper/2005.01819/) (2020)
- [Predicting Loose-Fitting Garment Deformations Using Bone-Driven Motion Networks](https://mlsanity.com/paper/2205.01355/) (2022)
- [Neural Cloth Simulation](https://mlsanity.com/paper/2212.11220/) (2022)
- [Dynamic Neural Garments](https://mlsanity.com/paper/2102.11811/) (2021)
- [FusedMM: A Unified SDDMM-SpMM Kernel for Graph Embedding and Graph Neural Networks](https://mlsanity.com/paper/2011.06391/) (2020)
- [Deep Detail Enhancement for Any Garment](https://mlsanity.com/paper/2008.04367/) (2020)
- [Motion Guided Deep Dynamic 3D Garments](https://mlsanity.com/paper/2209.11449/) (2022)
- [Liquid Splash Modeling with Neural Networks](https://mlsanity.com/paper/1704.04456/) (2017)
- [N-Cloth: Predicting 3D Cloth Deformation with Mesh-Based Networks](https://mlsanity.com/paper/2112.06397/) (2021)

## Built on by (most cited first, 5 of 5)

- [Garment3DGen: 3D Garment Stylization and Texture Generation](https://mlsanity.com/paper/2403.18816/) (2024)
- [Physics-aware Machine Learning Revolutionizes Scientific Paradigm for Machine Learning and Process-based Hydrology](https://mlsanity.com/paper/2310.05227/) (2023)
- [Neural Modular Physics for Elastic Simulation](https://mlsanity.com/paper/2512.15083/) (2025)
- [STMPL: Human Soft-Tissue Simulation](https://mlsanity.com/paper/2403.08344/) (2024)
- [HyperBones: Realtime Bone-driven Neural Garment Simulation with Hypernetwork Conditioning](https://mlsanity.com/paper/2605.20460/) (2026)

## Abstract (arXiv)

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.