A Game Changer CGI Methodology

A new deep learning method for more realistic CGI smoke and cloud effects.

A Game Changer CGI Methodology
There are two versions of the simulations, a rough draft version and a corresponding detailed, expensive one. (Image: Chu, Thuerey / TUM). In the embedded video from 2015 Prof. Nils Thuerey explains his research on simulating fluids.

You might have seen a movie from the early nineties. Have you ever observed that how far directors have progressed in their use of CGI -computer generated imagery that realistically simulating either parts of or entire scenes in a movie? Regardless, regular looking smoke and mists stay among the most troublesome impacts to recreate.

Having worked beforehand as the R&D lead on motion pictures, for example, “Iron Man 3” and “Super Man: Man of Steel” at the core of Hollywood at ScanlineVFX in Los Angeles, Nils Thuerey knows direct how tedious, dull and costly this procedure is.

Now, the professor is working at the Technical University of Munich (TUM) as a Professor for Games Engineering in the field of simulating liquids and gasses, which fall into the general category of fluids.

Now, he along with Ph.D. student Mengyu Chu has developed a new CGI methodology that introduces deep learning techniques into classical simulation algorithms. In their method, the algorithm learns from a pre-computed library. There are two versions of the simulations, a ‘cheap and rough draft version’ and a corresponding ‘finely detailed and expensive one’.

The calculation realizes which sets go together. When confronting another circumstance in another reproduction run, their calculation would then be able to look into the correct bit of information from the pre-registered library. Basically, the profound learning technique prepares a keen bookkeeper.

Chu said, “Our vision is to develop a broad library of simulations. It would allow producers on a small budget to take a cloud or smoke effect that had been created previously and edit it to fit their specific needs.”

“Right now, our work is most interesting for the movie industry. But our goal is to use it in the future for all kinds of realistic simulation – for example, in medicine. I’m particularly interested in blood flow in our bodies. It’s actually the same physics– fluid mechanics – as smoke.”

According to scientists, this CGI methodology could save time and money. They noted, in the emergency room of the future it could prove to be life-saving.