Transformer with Implicit Edges for Particle-based Physics Simulation

07/22/2022
by   Yidi Shao, et al.
14

Particle-based systems provide a flexible and unified way to simulate physics systems with complex dynamics. Most existing data-driven simulators for particle-based systems adopt graph neural networks (GNNs) as their network backbones, as particles and their interactions can be naturally represented by graph nodes and graph edges. However, while particle-based systems usually contain hundreds even thousands of particles, the explicit modeling of particle interactions as graph edges inevitably leads to a significant computational overhead, due to the increased number of particle interactions. Consequently, in this paper we propose a novel Transformer-based method, dubbed as Transformer with Implicit Edges (TIE), to capture the rich semantics of particle interactions in an edge-free manner. The core idea of TIE is to decentralize the computation involving pair-wise particle interactions into per-particle updates. This is achieved by adjusting the self-attention module to resemble the update formula of graph edges in GNN. To improve the generalization ability of TIE, we further amend TIE with learnable material-specific abstract particles to disentangle global material-wise semantics from local particle-wise semantics. We evaluate our model on diverse domains of varying complexity and materials. Compared with existing GNN-based methods, without bells and whistles, TIE achieves superior performance and generalization across all these domains. Codes and models are available at https://github.com/ftbabi/TIE_ECCV2022.git.

READ FULL TEXT

page 11

page 23

page 24

page 25

page 26

page 27

research
11/03/2021

Manipulation of granular materials by learning particle interactions

Manipulation of granular materials such as sand or rice remains an unsol...
research
11/18/2022

GNS: A generalizable Graph Neural Network-based simulator for particulate and fluid modeling

We develop a PyTorch-based Graph Network Simulator (GNS) that learns phy...
research
05/17/2023

Towards Multi-Layered 3D Garments Animation

Mimicking realistic dynamics in 3D garment animations is a challenging t...
research
04/10/2023

Faster Lead Optimization Mapper Algorithm for Large-Scale Relative Free Energy Perturbation

In recent years, free energy perturbation (FEP) calculations have garner...
research
07/26/2023

Graph Neural Networks-based Hybrid Framework For Predicting Particle Crushing Strength

Graph Neural Networks have emerged as an effective machine learning tool...
research
12/07/2022

Learning rigid dynamics with face interaction graph networks

Simulating rigid collisions among arbitrary shapes is notoriously diffic...

Please sign up or login with your details

Forgot password? Click here to reset