A Multi Pass GAN for Fluid Flow Super Resolution ( SCA 2019)
Authors:Maximilian Werhahn, You Xie, Mengyu Chu, Nils Thuerey; Technical University of Munich. Details at: Abstract: We propose a novel method to upsample volumetric functions with generative neural networks using several orthogonal passes. Our method decomposes generative problems on Cartesian field functions into multiple smaller subproblems that can be learned more efficiently. Specifically, we utilize two separate generative adversarial networks:
|
|