Over Two Million Lectures Given

We’re way beyond the point where words can describe how stunned I am by this. Thanks so much everyone! 🙂

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

Computational Fluid Dynamics For Simulation of Wind-Terrain Interaction in Flight Simulation

Manuel Dobusch has completed his Master thesis. It was co-supervised with Michael Wimmer and Eugene Zhang. Click on the image below to have a look!

thesis_dobusch

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

 

 

One Million Lectures Given

I was stunned to realize that we have reached one million views within the first year of Two Minute Papers! I have no idea how it happened, but thanks so much to you Fellow Scholars, I am honored to have supporters like you for the series!

1m-views

30

Two more and it’ll be a nice round number. 🙂

30

Separable Subsurface Scattering in Blender

A Separable Subsurface Scattering implementation has recently appeared in Blender! A big shoutout for Ľuboš Lenčo this fine piece of craftsmanship. Click on the image to have a look!

s4-blender

Jázmin Zsolnai-Fehér

We are delighted to share the news with you that our daughter Jázmin Zsolnai-Fehér was born today. The expected time of arrival for the baby was March 18th, with a significant non-zero variance. As you can see, she is currently lifting weights in her sleep and can’t wait to help her father coding neural networks and light transport algorithms. Jázmin is pronounced yah-zmin, which is a fair a bit easier to say than Károly is. Everyone is in good health and we are already working together!
jazmin_full
jazmin_2mp

Upsampling Fluid Simulations

My student, Felix König wrote a term paper on Upsampling Fluid Simulations. Click on the image to check it out!FelixKoenig_cgsem

Global Illumination in Participating Media

My student, Ádám Papp wrote a term paper on Global Illumination in Participating Media. Click on the image to check it out!AdamPapp_cgsem