While modern fluid simulation methods achieve high-quality simulation results, it is still a big challenge to interpret and control motion from visual quantities, such as the advected marker density. These visual quantities play an important role in user interactions: Being familiar and meaningful to humans, these quantities have a strong correlation with the underlying motion. We propose a novel data-driven conditional adversarial model that solves the challenging, and theoretically ill-posed problem of deriving plausible velocity fields from a single frame of a density field. Besides density modifications, our generative model is the first to enable the control of the results using all of the following control modalities: obstacles, physical parameters, kinetic energy, and vorticity. Our method is based on a new conditional generative adversarial neural network that explicitly embeds physical quantities into the learned latent space, and a new cyclic adversarial network design for control disentanglement. We show the high quality and versatile controllability of our results for density-based inference, realistic obstacle interaction, and sensitive responses to modifications of physical parameters, kinetic energy, and vorticity.



author = {Chu, Mengyu and Thuerey, Nils and Seidel, Hans-Peter and Theobalt, Christian and Zayer, Rhaleb},
title = {Learning Meaningful Controls for Fluids},
journal = {ACM Transactions on Graphics, (Proc. SIGGRAPH)},
month = {aug},
number = {4},
pages = {100:1-100:13},
volume = {40},
year = {2021},

Mengyu Chu, Nils Thuerey, Hans-Peter Seidel, Christian Theobalt, Rhaleb Zayer. 2021. Learning Meaningful Controls for Fluids. In ACM Transactions on Graphics, (Proc. SIGGRAPH), vol. 40, no. 4, 100:1-100:13, 2021.


For questions, clarifications, please get in touch with:
Mengyu Chu<mchu@mpi-inf.mpg.de>

Imprint. Data Protection.