An exclusive look at a new Google AI paper

I usually don’t post Two Minute Papers episodes here, but this time it is different. This work is as fresh as it gets because this is the first time I have been given an exclusive look before the paper came out, and this means that this video and the paper itself were published at the same time. I hope you will enjoy it just as much as I did!

Note: this is credited in the acknowledgments section of the paper.

 

Accelerating Eulerian Fluid Simulation With Convolutional Networks

Jonathan Tompson from Google and his colleagues, Kristofer Schlachter, Pablo Sprechmann and Ken Perlin from the New York University have come up with a really nice technique to teach a convolutional neural network how fluid and smoke simulations work. The project webpage is available here, or you can click on the image below to access the paper.

Status: accepted to ICML 2017

(please note that I am in the acknowledgements section and was not a co-author of the paper)

cnnfluid-cover

Surface-Only Liquids

Fang Da and his colleagues published an absolutely amazing paper on fluid simulations. Make sure to have a look, it is available here (or click on the paper below). I helped a bit with setting up the rendering pipeline and the scenes properly.

Status: accepted to ACM SIGGRAPH 2016

(please note that I am in the acknowledgements section and was not a co-author of the paper)

surfaceonlyliquids