arrow_drop_down

Deep Learning Beyond Cats and Dogs

Deep learning, which is seemingly everywhere these days, is well-known for its capability to recognize cats and dogs in internet images, but it can and should be used for other things too. It can be used to figure out the complicated physics that dictate fluid behaviour. Actually, simulating turbulence is not only a million dollar problem (really, google it!) but it can help us create more realistic virtual worlds. It can even help us understand medical and physiological behaviours, like blood flowing through our body. Nils performs cutting-edge research, and explains how neural networks are well on their way to becoming the fourth pillar of science.

About Nils Thuerey

Nils is an assistant professor at the Technical University of Munich. He works in the field of computer graphics and develops methods that use deep learning to model real world physical behaviors. One focus area of his research is developing fluid phenomena simulations to produce realistic depictions of fluids, such as water and smoke. These simulations are important for visual effects in computer-generated movies and digital games, and typically require huge amounts of computations in order to create a realistic picture to be shown on screen. Amongst other research, Nils and his team focus on developing novel algorithms to make simulations easier to control, to handle detailed surface tension effects, and to increase the amount of turbulent detail.

After studying computer science at the University of Erlangen-Nuremberg, Nils remained there and continued to work on simulating liquids, earning his PhD in 2006. Afterwards, he was a post-doctoral researcher at ETH Zurich until 2010. Nils was awarded a technical Oscar from the AMPAS in 2013 for his research on controllable smoke effects, and for developing a software that facilitates easier editing of explosions and smoke effects for films. Subsequently, he worked for three years as the R&D lead at the visual effects company ScanlineVFX, before he assumed his current position at TUM in October 2013.