Frequency-aware Interface Dynamics with Generative Adversarial Networks

Lukas Prantl, Tassilo Kugelstadt, Jan Bender, Nils Thuerey

Keywords: physical simulations, spatio-temporal dynamics, generative adversarial networks, fluids, elasto-plasticity

Abstract: We present a new method for reconstructing and refining complex surfaces based on physical simulations. Taking a roughly approximated simulation as input, our method infers corresponding spatial details while taking into account how they evolve over time. We consider this problem in terms of spatial and temporal frequencies, and leverage generative adversarial networks to learn the desired spatio-temporal signal for the surface dynamics. Furthermore, we investigate the possibility to train our network in an unsupervised manner, i.e. without predefined training pairs. We highlight the capabilities of our method with a set of synthetic wave function tests and complex 3D dynamics of elasto-plastic materials.

One-sentence Summary: We present a method for learning frequency-aware interface dynamics of physical systems such as fluids and elasto-plastic materials with Generative Adversarial Networks.

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics

Reviewed Version (pdf): https://openreview.net/references/pdf?id=hCLvI4cTz0