A Pioneering Neural Network Method for Efficient and Robust Fluid Simulation

TL;DR

This paper introduces a novel neural network approach for fluid simulation that is both efficient and robust, capable of handling complex environments with significantly improved speed and accuracy over traditional methods.

Contribution

It presents the first neural network model specifically designed for stable and efficient fluid simulation in complex scenarios, combining fluid dynamics modeling with momentum and stability constraints.

Findings

Speed increased by approximately 10 times over traditional SPH methods.

Simulation accuracy significantly improved compared to existing neural network algorithms.

Computational speed increased by over 300 times compared to traditional fluid simulation software.

Abstract

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.