Computer Graphics Laboratory ETH Zurich

ETH

Frequency-Aware Reconstruction of Fluid Simulations with Generative Networks

S. Biland, V. C. Azevedo, B. Kim, B. Solenthaler

Eurographics - Short Papers (Norrköping, Sweden, May 25-29, 2020), pp. 65-68

Abstract

Convolutional neural networks were recently employed to fully reconstruct fluid simulation data from a set of reduced parameters. However, since (de-)convolutions traditionally trained with supervised L1-loss functions do not discriminate between low and high frequencies in the data, the error is not minimized efficiently for higher bands. This directly correlates with the quality of the perceived results, since missing high frequency details are easily noticeable. In this paper, we analyze the reconstruction quality of generative networks and present a frequency-aware loss function that is able to focus on specific bands of the dataset during training time. We show that our approach improves reconstruction quality of fluid simulation data in mid-frequency bands, yielding perceptually better results while requiring comparable training time.

Downloads

Download Paper
[PDF]
Download Paper
[BibTeX]