Latent Space Subdivision: Stable and Controllable Time Predictions for Fluid Flow

2 code implementations • 12 Mar 2020 • Steffen Wiewel, Byung-soo Kim, Vinicius C. Azevedo, Barbara Solenthaler, Nils Thuerey

By selectively overwriting parts of the predicted latent space points, our proposed method is capable to robustly predict long-term sequences of complex physics problems.

Latent-space Physics: Towards Learning the Temporal Evolution of Fluid Flow

2 code implementations • 27 Feb 2018 • Steffen Wiewel, Moritz Becher, Nils Thuerey

We propose a method for the data-driven inference of temporal evolutions of physical functions with deep learning.

Dimensionality Reduction