Our Mission Statement

Two men and one woman in front of laptops talking.

Our Vision

As a leading entrepreneurial university, we are a site of global knowledge exchange, shaping a sustainable future through talent, excellence and responsibility.

Our Mission

We inspire, promote and develop talents in all their diversity to become responsible, broad-minded individuals. We empower them to shape the progress of innovation for people, nature, and society with scientific excellence and technological expertise, with entrepreneurial courage and sensitivity to social and political issues, as well as a lifelong commitment to learning.

Our Core Values

Our core values form the foundation of our relationships with one another and with our cooperation partners:

  • Excellence: We cultivate an environment of curiosity, creativity and unconventional thinking across the disciplines and set the highest standards of performance in research, teaching, and innovation.
  • Entrepreneurial Mindset: We question the consequences of our actions, take on new challenges proactively, and continually enhance our working methods. We commit ourselves to socially reflected innovations and promote their commercial application by founding sustainable technology spin-offs.
  • Integrity: We draw our success from an inclusive community of talents from different backgrounds, cultures, ideas and perspectives. We act with respect for others and transparency in accordance with our shared values.
  • Collegiality: We respect and inspire one another in a vibrant culture of university community. We cultivate the academic, economic and social partnerships that make TUM a site of global knowledge exchange.
  • Sustainability and Resilience: We learn from our diverse experiences and see in persistent change the opportunity for the sustainable development of science, ecology, economy and society – from this we draw inspiration, motivation and resolve.

Our Guiding Principles

Governing Documents

An overview of central codes and regulations by which we shape research and innovation, teaching, and our governance as a top and modern university of international standing.

Governing Documents

Compliance

The TUM Compliance Office ensures the integrity and transparency of research, teaching and innovation based on the TUM Code of Conduct, the TUM Respect Guide, and the Statute on Safeguarding Good Academic Practice.

TUM Compliance Office

Image brochure "Global Hub of Knowledge Exchange"

We show who we are, what will drive us in the future and what makes us tick, through exciting research projects, insights into the future organizational structure and with stories of visionaries, founders and pioneers.

Explore now

News

  • 12/5/2017

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

Casting call for clouds

Compare any movie from the early nineties with one from 2017, and you’ll see just how far moviemakers have progressed in their use of CGI – computer generated imagery – for realistically simulating either parts of or entire scenes in a movie. Nonetheless, natural-looking smoke and clouds remain among the most difficult effects to simulate. Researchers at the Technical University of Munich (TUM) have now developed a new CGI methodology that promises to be a game changer.

There are two versions of the simulations, a rough draft version and a corresponding detailed, expensive one. In the embedded video Prof. Nils Thuerey explains his research on simulating fluids.
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.

Having worked previously as the R&D lead on movies such as "Iron Man 3" and "Super Man: Man of Steel" at the heart of Hollywood at ScanlineVFX in Los Angeles, Nils Thuerey knows first-hand how time consuming, tedious and expensive this process is. He already has one Technical Oscar Award under his belt for his groundbreaking work in the field of physics simulations for visual effects and CGI. At the TUM, the Professor for Games Engineering works in the field of simulating liquids and gasses, which fall into the general category of fluids.

Rendering the vast amount of detail and the complex motions visible in real-life smoke clouds has been a long-standing challenge for fluid simulations in computer graphics. "Representing the fine features you see in real smoke or clouds typically requires very fine-grained spatial resolutions in a simulation," explains Ph.D. student Mengyu Chu. "This takes up a lot of computational resources and results in very costly simulation runs with painfully long turnaround times in the production process."

Thuerey adds: "Just one simulation for a single smoke cloud can take a day to produce – sometimes longer. And, at the end of the day, if the director doesn’t like what the graphic artist or programmer has produced, you have to throw everything away and start from scratch with a new simulation."

The smart librarian

Now Thuerey and Chu have developed a new methodology that introduces deep learning techniques into classical simulation algorithms. Deep learning is part of a broader family of machine learning methods based on learning representations from large amounts of data.

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 algorithm learns which pairs go together. When facing a new situation in another simulation run, their algorithm can then look up the right piece of data from the pre-computed library. Essentially, the deep learning method trains a "smart librarian."

From the movies to medicine and beyond

Chu and Thuerey say their 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," says Chu.

"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," says Thuerey. "I’m particularly interested in blood flow in our bodies. It’s actually the same physics – fluid mechanics – as smoke." For movie studios, the new method could save time and money – but in the emergency room of the future it could prove to be life-saving.

---

The research is part of the "realFlow – Virtualization of Real Flows for Animation and Simulation" project, for which Thurey received a starting grant from the European Research Council in 2015. The research project aims at the ability to run simulations of physical processes better and, above all, faster.

Publication:

Mengyu Chu, Nils Thuerey: “Data-Driven Synthesis of Smoke Flows with CNN-based Feature Descriptors”, ACM Transactions on Graphics (SIGGRAPH 2017), Vol. 36 (4), Article No. 69
DOI: 10.1145/3072959.3073643
http://ge.in.tum.de/publications/2017-sig-chu/

Images for editorial use

mediatum.ub.tum.de/1416445

More information:

Contact:

Prof. Dr.-Ing. Nils Thuerey
Department for Informatics
eMail: nils.thuerey@tum.de
Phone: +49 89 289 19484

Mengyu Chu
E-mail: mengyu.chu@tum.de
Phone: +49.89.289.19482

Technical University of Munich

Corporate Communications Center

Back to list
HSTS