Lecture: Advanced Deep Learning for Graphics


  • Lecturer(s):
  • Start: 22.04.2020
  • Dates: Wed. 12:15 - 13:45, tbd
  • Course number: MA-INF 2217
  • Curriculum: Master
  • Effort: 4.0 SWS
  • Exams: 28 July 2020 (room reservation: 12:00 - 15:00) and 28 September 2020 (room reservation: 13:00 - 16:00)


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





[MAILING LIST] Hello, the mailing list for the course is now up and running. 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 !

[2nd Exam] The second ADLG exam will be held on Monday the 28th of September from 1200 - 1330 hours at Wolfgang-Paul-Hörsaal.

Before attending the exam, please check the following link and get familiarised with the instructions and guidelines provided by the university.

https://www.uni-bonn.de/die-universitaet/informationen-zum-coronavirus/handout-for-on-site-examinations-2013-information-for-students/at_download/file https://www.uni-bonn.de/die-universitaet/informationen-zum-coronavirus/handout-for-on-site-examinations-2013-information-for-students/at_download/file


Assignment Sheets

Exercise 1: Introduction
Assignment sheet  (PDF document, 288 KB)
Exercise 2: RNNs and GANs
Assignment sheet  (PDF document, 146 KB)
Exercise 3: Image-to-Image Translation
Assignment sheet  (PDF document, 2.0 MB)
Exercise 4: Optical Material Properties and 3D Data
Assignment sheet  (PDF document, 50 KB)
Exercise 5: PointNet
Assignment sheet  (PDF document, 77 KB)

Additional Documents