A Pioneering Neural Network Method for Efficient and Robust Fluid Simulation
Not on the map. Why?
Abstract (arXiv)
Fluid simulation is an important research topic in computer graphics (CG) and animation in video games. Traditional methods based on Navier-Stokes equations are computationally expensive. In this paper, we treat fluid motion as point cloud transformation and propose the first neural network method specifically designed for efficient and robust fluid simulation in complex environments. This model is also the deep learning model that is the first to be capable of stably modeling fluid particle dynamics in such complex scenarios. Our triangle feature fusion design achieves an optimal balance among fluid dynamics modeling, momentum conservation constraints, and global stability control. We conducted comprehensive experiments on datasets. Compared to existing neural network-based fluid simulation algorithms, we significantly enhanced accuracy while maintaining high computational speed. Compared to traditional SPH methods, our speed improved approximately 10 times. Furthermore, compared to traditional fluid simulation software such as Flow3D, our computation speed increased by more than 300 times.
Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 20 of its 32 references that are in the map. First posted on arXiv 14 Dec 2024.
Builds on
20 of 32 references.
References · 20
- 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,248
- 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,401
- 2018Dynamic Graph CNN for Learning on Point Cloudscited by 2,223
- 2019KPConv: Flexible and Deformable Convolution for Point Cloudscited by 1,205
- 2020Learning to Simulate Complex Physics with Graph Networkscited by 880
- 2016Interaction Networks for Learning about Objects, Relations and Physicscited by 509
- 2021Physics-informed neural networks (PINNs) for fluid mechanics: A reviewcited by 473
- 2018Learning Particle Dynamics for Manipulating Rigid Bodies, Deformable Objects, and Fluidscited by 220
- 2021Deep Parametric Continuous Convolutional Neural Networkscited by 161
- 2016Accelerating Eulerian Fluid Simulation With Convolutional Networkscited by 130
- 2018Flexible Neural Representation for Physics Predictioncited by 91
- 2022Guaranteed Conservation of Momentum for Learning Particle-based Fluid Dynamicscited by 30
8 more
- 2022Transformer with Implicit Edges for Particle-based Physics Simulationcited by 15
- 2022Copy Motion From One to Another: Fake Motion Video Generationcited by 13
- 2020Physics-Incorporated Convolutional Recurrent Neural Networks for Source Identification and Forecasting of Dynamical Systemscited by 12
- 2020Smoothed Particle Hydrodynamics Techniques for the Physics Based Simulation of Fluids and Solidscited by 9
- 2024Do As I Do: Pose Guided Human Motion Copycited by 8
- 2024Symmetric Basis Convolutions for Learning Lagrangian Fluid Mechanicscited by 4
- 2023DualFluidNet: an Attention-based Dual-pipeline Network for FLuid Simulationcited by 2
- 2023Rotation-Invariant Completion Networkcited by 1
Built on by
Citing papers per year: 2025: 1.
1 paper.