Fakultät Informatik

Deep Learning and Numerical Simulations for Visual Effects

Further reading: additional papers of Prof. Thuerey's group on physics-based deep learning for fluids  can be found here. Selected examples include:

 


 Prof. Dr. Nils Thuerey ,  Marie-Lena Eckert

Deep Learning and Numerical Simulations for Visual Effects (IN 2298)

Time, Place:

Wednesday , 16:00,  HS2

Thursday, 10:00,  HS2

First lecture: Thu., Apr. 27.,2017

Prerequisites:

Computer Graphics and Game Physics highly recommended

Materials:

moodle page

Exam:

tba

+

Content

This course targets machine learning techniques and numerical simulation
algorithms for materials such as fluids and deformable objects in the context
of computer animation. The lecture and exercises will all be in English. The following topics are discussed:

  • Convolutional neural networks & deep learning techniques
  • Physically-based animation, fluid modeling
  • Discretizations, and partial differential equations
  • Exercises to gain hands-on experience with CNN training and fluid simulation algorithms

Prerequisites

Computer Gaphics Fundamentals, and Game Physics (Lagrangian simulation techniques)

Literature

 

Machine Learning

Fluid Simulation

General Background

 

  • Introduction to Linear Algebra: Gilbert Strang, Wellesley-Cambridge Press

  • Computer Animation: Algorithms and Techniques, Parent, Morgan Kaufmann

 

 

 

Lecture Slides

Will be made available on the moodle page

 

News

- In collaboration with partners from industry, we have a number of thesis topics available in the area of point-based rendering, geo-localization using public data, scene fusion from different viewpoints. If you are interested, please contact  westermann(at)tum.de

 

- One PhD position on   Turbulence Visualization is available at the Computer Graphics & Visualization group.