作者
Jonathan Tompson, Kristofer Schlachter, Pablo Sprechmann, Ken Perlin
发表日期
2017/7/17
研讨会论文
International conference on machine learning
页码范围
3424-3433
出版商
PMLR
简介
Efficient simulation of the Navier-Stokes equations for fluid flow is a long standing problem in applied mathematics, for which state-of-the-art methods require large compute resources. In this work, we propose a data-driven approach that leverages the approximation power of deep-learning with the precision of standard solvers to obtain fast and highly realistic simulations. Our method solves the incompressible Euler equations using the standard operator splitting method, in which a large sparse linear system with many free parameters must be solved. We use a Convolutional Network with a highly tailored architecture, trained using a novel unsupervised learning framework to solve the linear system. We present real-time 2D and 3D simulations that outperform recently proposed data-driven methods; the obtained results are realistic and show good generalization properties.
学术搜索中的文章
J Tompson, K Schlachter, P Sprechmann, K Perlin - International conference on machine learning, 2017
J Tompson, K Schlachter, P Sprechmann, K Perlin - arXiv preprint arXiv:1607.03597, 2017
J Tompson, K Schlachter, P Sprechmann, K Perlin - arXiv preprint arXiv:1607.03597, 2016
J Tompson, K Schlachter, P Sprechmann, K Perlin - International Convention Centre, Sydney, Australia, 2017