Fakultät Informatik

Master-Seminar – Deep Learning in Computer Graphics


 Nils Thuerey,  Rüdiger Westermann,  Kiwon Um,  Rachel Chu


Master Informatics

Time, Place

Mondays 16:00-18:00, Seminar room:  MI 02.13.010


9 April 2018


In this course, students will autonomously investigate recent research about machine learning techniques in computer graphics. Independent investigation for further reading, critical analysis, and evaluation of the topic are required.



  • It is only allowed to miss a single time-slot. Missing a second one means failing the seminar. If you have to miss any, please let us know in advance.

Presentation (slides)

  • You will present your topic in English, and the talk should last 30 minutes.
  • The slides should be structured according to your presentation. You can use any layout or template you like.
  • Plagiarism is important; please do not simply copy the original authors' slides. You can certainly refer to them.
  • The semi-final slides (PDF) should be sent one week before the talk; otherwise, the talk will be canceled.
  • We strongly encourage you to finalize the semi-final version as far as possible. We will take a look at the version and give feedback. You can revise your slides until your presentation.


  • A short report (4 pages max. excluding references in  the ACM SIGGRAPH TOG format (acmtog) - you can download the precompiled latex template) should be prepared and sent within two weeks after the talk, i.e., by 23:59 on Monday. When you send the report, please send the final slides (PDF) together.
  • Guideline: You can begin with writing a summary of the work you present as a start point; but, it would be better if you focus more on your own research rather than just finishing with the summary of the paper. We, including you, are not interested in revisiting the work done before; it is more meaningful if you make an effort to put your own reasoning about the work, such as pros and cons, limitation, possible future work, your own ideas for the issues, etc.

Preliminary Schedule

16 March 2018

Deadline for sending an e-mail with 3 preferences

23 March 2018

Notification of assigned paper





09 Apr 2018

No Lecture


16 Apr 2018

Dominik Fuchsgruber

2016, Dong et al.,  Image Super-Resolution Using Deep Convolutional Networks, IEEE Trans. Pattern Anal. Mach. Intell.

16 Apr 2018

Mert Ülker

2017, Dahl et al.,  Pixel Recursive Super Resolution, arXiv.org

23 Apr 2018

Vladimir Poliakov

2014, Goodfellow et al.,  Generative Adversarial Networks, Advances in Neural Information Processing Systems 27

23 Apr 2018

Daniel Matter

2015, Mnih et al.,  Human-Level Control Through Deep Reinforcement Learning, Nature


Ahmad Tahir

2015, Gryka et al.,  Learning to Remove Soft Shadows, ACM Trans. Graph.

30 Apr 2018

Konstantin Weißenow

2017, Li et al.,  Deep Extraction of Manga Structural Lines, ACM Trans. Graph.

07 May 2018

Khushbu Saxena

2016, Ruder et al.,  Artistic Style Transfer for Videos, GCPR
(optional) 2015, Gatys et al.,  A Neural Algorithm of Artistic Style, arXiv.org

07 May 2018

Maheswaran Rajesh

2017, Wang et al.,  O-CNN: Octree-based Convolutional Neural Networks for 3D Shape Analysis, ACM Trans. Graph.

14 May 2018

Martin Eisenmann

2017, Chu and Thuerey,  Data-driven Synthesis of Smoke Flows with CNN-based Feature Descriptors, ACM Trans. Graph.

14 May 2018

Fabian Kilger

2018, Xie et al.,  tempoGAN: A Temporally Coherent, Volumetric GAN for Super-resolution Fluid Flow, arXiv.org

21 May 2018

No Talk

Whit Monday

28 May 2018

Jeremias Bohn

2016, Peng et al.,  Terrain-adaptive Locomotion Skills Using Deep Reinforcement Learning, ACM Trans. Graph.

28 May 2018

Moritz Becher

2017, Holden et al.,  Phase-functioned Neural Networks for Character Control, ACM Trans. Graph.

04 Jun 2018

Jan Ahlbrecht

2017, Suwajanakorn et al.,  Synthesizing Obama: Learning Lip Sync from Audio, ACM Trans. Graph.

04 Jun 2018

Kaan Bagci

2017, Karras et al.,  Audio-driven Facial Animation by Joint End-to-end Learning of Pose and Emotion, ACM Trans. Graph.

11 Jun 2018

Kilian Schmidt

2017, Gharbi et al.,  Deep Bilateral Learning for Real-time Image Enhancement, ACM Trans. Graph.

11 Jun 2018

Malte Schmitz

2017, Bako et al.,  Kernel-predicting Convolutional Networks for Denoising Monte Carlo Renderings, ACM Trans. Graph.

You can access the papers through TUM library's  eAccess.




Bachelor and Master thesis in the following areas:
- A remote rendering system for point cloud data (in collaboration with industry)

- Deep learning for improved weather forecasting

- Learning trajectory clustering using neural network
- Learning Level-of-Detail representations for point clouds

- 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.