Computer Graphics Forum (SCA 2018), Vol. 37 (8)

Kiwon Um, Technical University of Munich
Xiangyu Hu, Technical University of Munich
Nils Thuerey, Technical University of Munich

This paper proposes a new data-driven approach to model detailed splashes for liquid simulations with neural networks. Our model learns to generate small-scale splash detail for the fluid-implicit-particle method using training data acquired from physically parameterized, high resolution simulations. We use neural networks to model the regression of splash formation using a classifier together with a velocity modifier. For the velocity modification, we employ a heteroscedastic model. We evaluate our method for different spatial scales, simulation setups, and solvers. Our simulation results demonstrate that our model significantly improves visual fidelity with a large amount of realistic droplet formation and yields splash detail much more efficiently than finer discretizations.

splash, neural networks, machine learning, liquid simulation, fluid-implicit-particle (FLIP)

Wiley Online Library, Preprint
Video (YouTube)

This work is supported by the ERC Starting Grant 637014.