Direkt zum Inhalt springen
Computer Vision Group
TUM Department of Informatics
Technical University of Munich

Technical University of Munich



Selected Topics in Variational Image Processing

Seminar for computer science master students (IN2107) and mathematics bachelor and master students.

WS 2014/15, TU München


Location: Room 02.09.23
Date: Wednesday, First meeting 02.07.2014 (17:30-19:30), Presentations starting on 19.11.2014
Time: 14:00 - 16:00
Lecturer: Michael Möller, Thomas Möllenhoff, Mohamed Souiai
SWS: 2

The course will be held in English. The students can do their presentation in German, but English is preferred.


Variational methods have proven to be one of the most effective tools in tackling image processing problems and still are an active field of research. This seminar deals with recent advances in the field of variational image processing for particular applications. Participants will see detailed examples for how different problems can be tackled with similar techniques, namely by formulating variational approaches. While the lecture “Variational Methods for Computer Vision” gives a general introduction and overview of the field, this seminar will allow students to study one variational method for a particular problem in detail and could therefore prepare them for their own research in this field.

The focus of the seminar will be on modelling different problems in a variational framework. Each Student selects a scientific publication which she/he presents at the seminar.

Number of participants: 15 Students (Master).
Registration: On TUM online.
After the registration: Send an e-Mail with your name and your three favorite topics (ranked 1,2,3) to Michael Möller.

LaTeX-Template for the Report

A LaTeX-template for your seminar report is available for download here.

Slides from the first meeting

The slides from the first meeting can be found here here. The slides are password protected. Please send an email to moellerm(at)in.tum.de in case you are interested in the slides but do not know the password.

Any participant that missed the first meeting should look at the Slides of the first meeting. If you still have questions, please do not hesitate to ask by email to Michael Möller.


Meetings will always take place on Wednesday 14:00 in room 02.09.023.

Topic Title Date Supervisor Student
1 Introduction to Total Variation for Image Analysis Wednesday 14:00 Nov 19, 2014 Thomas Möllenhoff Nitin Deshpande
2 Examplar-Based Image Inpainting Wednesday 15:00 Nov 19, 2014 Mohamed Souiai Tim Wiese
3 Linear Diffusion based Image Compression with iPiano Wednesday 14:00 Dec 03, 2014 Thomas Möllenhoff Mohammad Moein
4 Image Demosaicking Wednesday 15:00 Dec 03, 2014 Michael Moeller Rüdiger Göbl
5 Pan Sharpening Wednesday 14:00 Dec 10, 2014 Michael Moeller Sahand Yousefpourlazarjani
6 Variational Optical Flow Wednesday 15:00 Dec 10, 2014 Mohamed Souiai Ozge Akin
7 Globally optimal two phase segmentation Wednesday 14:00 Dec 17, 2014 Mohamed Souiai Adrian Haarbach
8 Multilabel Segmentation Wednesday 15:00 Dec 17, 2014 Mohamed Souiai Quirin Fischer

Rechte Seite

Informatik IX
Chair of Computer Vision & Artificial Intelligence

Boltzmannstrasse 3
85748 Garching info@vision.in.tum.de

Follow us on:
CVG Group DVL Group



Bernt Schiele (Max Planck Institute for Informatics) will give a talk in the TUM AI lecture series on June 10th, 3pm! Livestream

French-German Machine Learning Symposium

French-German Machine Learning Symposium

The French-German Machine Learning Symposium aims to strengthen interactions and inspire collaborations between both countries. We invited some of the leading ML researchers from France and Germany to this two-day symposium to give a glimpse into their research, and engage in discussions on the future of machine learning and how to strengthen research collaborations in ML between France and Germany.

The list of speakers includes Yann LeCun, Cordelia Schmid, Jean-Bernard Lasserre, Bernhard Schölkopf, and many more! For the full program please visit the webpage.


Ron Kimmel (Technion - Israel Institute of Technology) will give a talk in the TUM AI lecture series on May 6th, 3pm! Livestream


4Seasons Dataset: We have released a novel dataset for benchmarking multi-weather SLAM in autonomous driving.


Hao Li (Pinscreen) will give a talk in the TUM AI lecture series on April 22nd, 8pm! Livestream