Lecture: Advanced Deep Learning for Graphics


  • Lecturer(s):
  • Start: 14.04.2021
  • Dates: Wed. 12:15 - 13:45, online via ZOOM
  • Course number: MA-INF 2217
  • Curriculum: Master
  • Effort: 4.0 SWS
  • Exams: tbd


  • Tutor(s):
  • Start: TBA via mailing list
  • Dates: tbd


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).


Please inscribe yourself into the mailing list at : https://lists.iai.uni-bonn.de/mailman/listinfo.cgi/vl-adlg

The mailing list will serve as the first and main source of information for notifying the course participants on release of new exercises, sudden changes to the lecture schedules, and other relevant information. Additionally, it provides a place where students can discuss freely about the lecture, exercises, so please do not hesitate to ask and reply !





Assignment Sheets

Exercise 1: Intro (Practical)
Assignment sheet  (PDF document, 149 KB)
Exercise 1: Intro (Theory)
Assignment sheet  (PDF document, 251 KB)