The paper “Accelerating Eulerian Fluid Simulation With Convolutional Networks” and its source code is available here:
The mentioned previous work has used an SPH-based Lagrangian simulation, performed the regression with regression forests, and the process also has included a fair amount of feature engineering. It is an excellent piece of work by the name “Data-driven Fluid Simulations using Regression Forests” and is a highly recommended read:
Video credits:
Surface-Only Liquids –
Schrödinger’s Smoke –
Thumbnail image background credit:
WE WOULD LIKE TO THANK OUR GENEROUS PATREON SUPPORTERS WHO MAKE TWO MINUTE PAPERS POSSIBLE:
Sunil Kim, Daniel John Benton, Dave Rushton-Smith, Benjamin Kang.
Subscribe if you would like to see more of these! –
Music: Dat Groove by Audionautix is licensed under a Creative Commons Attribution license (
Artist:
Splash screen/thumbnail design: Felícia Fehér –
Károly Zsolnai-Fehér’s links:
Facebook →
Twitter →
Web →
source
