On Wednesday, 24.07.2019, 12:15, we will be available for questions (we will meet in front of HS3+4, in case they are booked we will be in the neigboring building (Endenicher Allee 19A) in room 3.035b).


Please send your questions via mail to both and until Tuesday, 12:00 to allow a more efficient handling.


Please also feel free to send us questions earlier. We will collect them in a pdf that will be available to you in the documents section of the course-webpage where we also try to add the answers as early as possible.


UPDATE : If you would like to see your exam copy for the second attempt, please set up an appointment with the tutor via email.

Vorlesung: Advanced Deep Learning for Graphics


  • Dozent(en):
  • Beginn: 10.04.2019
  • Zeiten: Wed. 12:15 - 13:45 HS 4
  • Veranstaltungsnummer: MA-INF 2217
  • Studiengang: Master
  • Aufwand: 2.0 SWS
  • Prüfungen: 25.7., 14:00-17:00, HS3+4,5+6,7, 19.9., 9:00-12:00, HS5+6,7


  • Betreuer:
  • Beginn: 27.4.
  • Zeiten: see BASIS and via appointment (with Soumajit Majumder)


This course focuses on cutting-edge Deep Learning techniques for computer graphics. After a brief review of CNNs the focus will be laid on autoencoders, generative models and the extension of these methods to graph- and manifold-structured data.  Applications discussed will include inverse problems in computer graphics and the synthesis of models including data completion and super-resolution.

The course will build upon the basics of machine learning as well as fundamentals and basic architectures of neural networks. Therefore, it is highly recommended to have taken Deep Learning for Visual Recognition or a similar course as a prerequisite. Exercises will be a mix of theory and practical (Python).





Übung 1: Autoencoder
Übungsblatt  (PDF-Dokument, 141 KB)
Übung 2: ImageSegmentation
Übungsblatt  (PDF-Dokument, 527 KB)
Übung 3: Superresolution
Übungsblatt  (PDF-Dokument, 689 KB)
Übung 4: 3DDeepLearning
Übungsblatt  (PDF-Dokument, 134 KB)

Weitere Dokumente