1 code implementation • 2 May 2020 • Byung-soo Kim, Vinicius C. Azevedo, Markus Gross, Barbara Solenthaler
Artistically controlling the shape, motion and appearance of fluid simulations pose major challenges in visual effects production.
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.
no code implementations • 18 Dec 2019 • Fabienne Christen, Byung-soo Kim, Vinicius C. Azevedo, Barbara Solenthaler
Artistically controlling fluid simulations requires a large amount of manual work by an artist.
Graphics
no code implementations • 18 Dec 2019 • Simon Biland, Vinicius C. Azevedo, Byung-soo Kim, Barbara Solenthaler
Convolutional neural networks were recently employed to fully reconstruct fluid simulation data from a set of reduced parameters.
no code implementations • 17 May 2019 • Byung-soo Kim, Vinicius C. Azevedo, Markus Gross, Barbara Solenthaler
Optimization techniques rely on approximating simulation states towards target velocity or density field configurations, which are often handcrafted by artists to indirectly control smoke dynamics.
1 code implementation • 6 Jun 2018 • Byung-soo Kim, Vinicius C. Azevedo, Nils Thuerey, Theodore Kim, Markus Gross, Barbara Solenthaler
This paper presents a novel generative model to synthesize fluid simulations from a set of reduced parameters.