Physics Forests real-time fluids solver
Nov 02, 2015 by CGP Staff
0
|
Researchers from ETH Zurich have come up with a novel machine learning based method for physics-based fluid simulation. The GPU implementation provides a speedup of one to three orders of magnitude compared to current position-based fluid solvers, allowing it to run in real-time for systems with up to 2 million particles and enabling user interaction. More on ETH Zurich’s website.