2024/12/14 by Chen Yu, Shuai Zheng, Chen, Yu +7 · 1 citation
Engineering · #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #FOS: Physical sciences #Fluid Dynamics (physics.flu-dyn) #Fluid Dynamics Simulations and Interactions #Graphics (cs.GR) #Hydraulic and Pneumatic Systems #Machine Learning (cs.LG) #Nuclear Engineering Thermal-Hydraulics
paper · pdf · doi:10.48550/arxiv.2412.10748
openalex publication_date 2024/12/14 · openalex created_date 2024/12/18 · openalex updated_date 2026/07/28
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.