Lecture: Advanced Deep Learning for Graphics

Course

  • Lecturer(s):
  • Start: 22.04.2020
  • Dates: Wed. 12:15 - 13:45, tbd
  • Course number: MA-INF 2217
  • Curriculum: Master
  • Effort: 2.0 SWS
  • Exams: tbd

Exercises

  • Tutor(s):
  • Start: TBA via mailing list
  • Dates: see BASIS and via appointment (with Soumajit Majumder)

Description

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).

 

 

 

News

[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 !

[LECTURE ORGANIZATION] Due to the current circumstances we are forced to change the teaching style:
1. We will stream lectures via zoom. You get the respective invitations and passwords via the mailing list.
2. Lecture materials will be made accessible here as previously as well as in eCampus. In case of questions, please consider contacting us via chat (details will be provided) or we can arrange an online meeting.
3. We will accept online submissions for the exercise sheets and the  presentation of the final project will also be held via zoom.

Slides

Assignment Sheets

Exercise 1: Introduction
Assignment sheet  (PDF document, 288 KB)
Exercise 2: RNNs and GANs
Assignment sheet  (PDF document, 146 KB)