EqCollide: Equivariant and Collision-Aware Deformable Objects Neural Simulator
Not on the map. Why?
Abstract (arXiv)
Simulating collisions of deformable objects is a fundamental yet challenging task due to the complexity of modeling solid mechanics and multi-body interactions. Existing data-driven methods often suffer from lack of equivariance to physical symmetries, inadequate handling of collisions, and limited scalability. Here we introduce EqCollide, the first end-to-end equivariant neural fields simulator for deformable objects and their collisions. We propose an equivariant encoder to map object geometry and velocity into latent control points. A subsequent equivariant Graph Neural Network-based Neural Ordinary Differential Equation models the interactions among control points via collision-aware message passing. To reconstruct velocity fields, we query a neural field conditioned on control point features, enabling continuous and resolution-independent motion predictions. Experimental results on 2D and 3D scenarios show that EqCollide achieves accurate, stable, and scalable simulations across diverse object configurations. It achieves 24.34% to 57.62% lower rollout MSE, even compared with the best-performing baseline model. Furthermore, EqCollide could generalize to more colliding objects and extended temporal horizons, and stay robust to input transformed with group action. Code is available at: https://github.com/AI4Science-WestlakeU/EqCollide
Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 36 of its 50 references that are in the map. First posted on arXiv 6 Jun 2025.
Builds on
36 of 50 references.
References · 36
- 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,401
- 2018Neural Ordinary Differential Equationscited by 3,779
- 2019DeepSDF: Learning Continuous Signed Distance Functions for Shape Representationcited by 2,689
- 2020Implicit Neural Representations with Periodic Activation Functionscited by 2,238
- 2018Occupancy Networks: Learning 3D Reconstruction in Function Spacecited by 2,041
- 2018Learning Implicit Fields for Generative Shape Modelingcited by 1,060
- 2021E(n) Equivariant Graph Neural Networkscited by 965
- 2020Learning to Simulate Complex Physics with Graph Networkscited by 880
- 2020Learning Mesh-Based Simulation with Graph Networkscited by 868
- 2018Tensor field networks: Rotation- and translation-equivariant neural networks for 3D point cloudscited by 746
- 2016Interaction Networks for Learning about Objects, Relations and Physicscited by 509
- 2020Lagrangian Neural Networkscited by 398
24 more
- 2021GemNet: Universal Directional Graph Neural Networks for Moleculescited by 343
- 2021Vector Neurons: A General Framework for SO(3)-Equivariant Networkscited by 305
- 2018Graph networks as learnable physics engines for inference and controlcited by 244
- 2021Geometric and Physical Quantities Improve E(3) Equivariant Message Passingcited by 228
- 2018Learning Particle Dynamics for Manipulating Rigid Bodies, Deformable Objects, and Fluidscited by 220
- 2020MetaSDF: Meta-learning Signed Distance Functionscited by 214
- 2022From data to functa: Your data point is a function and you can treat it like onecited by 187
- 2019An Energy Approach to the Solution of Partial Differential Equations in Computational Mechanics via Machine Learning: Concepts, Implementation and Applicationscited by 118
- 2019Hamiltonian Graph Networks with ODE Integratorscited by 108
- 2022Equivariant Graph Mechanics Networks with Constraintscited by 68
- 2024Graph Neural Networks for Learning Equivariant Representations of Neural Networkscited by 59
- 2022Efficient Learning of Mesh-Based Physical Simulation with BSMS-GNNcited by 45
- 2022Learning rigid dynamics with face interaction graph networkscited by 43
- 2023Fast, Expressive SE(n) Equivariant Networks through Weight-Sharing in Position-Orientation Spacecited by 41
- 2022Learning Physical Dynamics with Subequivariant Graph Neural Networkscited by 39
- 2022Implicit Neural Spatial Representations for Time-dependent PDEscited by 35
- 2021Extending Lagrangian and Hamiltonian Neural Networks with Differentiable Contact Modelscited by 34
- 2021Conditional Neural Relational Inference for Interacting Systemscited by 28
- 2021Constraint-based graph network simulatorcited by 27
- 2024Grounding Continuous Representations in Geometry: Equivariant Neural Fieldscited by 19
- 2024Space-Time Continuous PDE Forecasting using Equivariant Neural Fieldscited by 18
- 2023Fluid Simulation on Neural Flow Mapscited by 12
- 2024Learning rigid-body simulators over implicit shapes for large-scale scenes and visioncited by 12
- 2025Geometry aware inference of steady state PDEs using Equivariant Neural Fields representationscited by 6
Built on by
Citing papers per year: 2026: 1.
1 paper.