Persönlicher Status und Werkzeuge

Home Teaching Winter Semester 2016/17 Computer Vision I: Variational Methods

Computer Vision I: Variational Methods

WS 2016/17, TU München


Location: Room 02.09.023
Time and Date:
Wednesday, 10.15h - 11.45h
Thursday, 10.15h - 11.00h
Lecturer: Prof. Dr. Daniel Cremers

The lectures are held in English.


Location: Room 02.09.023
Time and Date: Monday, 9.15h - 11.30h
Organization: Thomas Möllenhoff, David Schubert


Location: Room 5620.01.102 (Interims Hörsaal 2)
Time and Date: Tuesday, February 28, 2017, 8.00h - 10.00h

You may only use standard writing materials. No cheat sheet, no electronic devices.

The retry exam will take place on April 20, 2017, 16.00h-18.00h.


Variational Methods are among the most classical techniques for optimization of cost functions in higher dimension. Many challenges in Computer Vision and in other domains of research can be formulated as variational methods. Examples include denoising, deblurring, image segmentation, tracking, optical flow estimation, depth estimation from stereo images or 3D reconstruction from multiple views.

In this class, I will introduce the basic concepts of variational methods, the Euler-Lagrange calculus and partial differential equations. I will discuss how respective computer vision and image analysis challenges can be cast as variational problems and how they can be efficiently solved. Towards the end of the class, I will discuss convex formulations and convex relaxations which allow to compute optimal or near-optimal solutions in the variational setting.


The requirements for the class are knowledge in basic mathematics, in particular multivariate analysis and linear algebra. Some prior knowledge on optimization is a plus but is not necessary.

Lecture Material

Course material (slides and exercise sheets) can be accessed here.

Please email David Schubert for password request.

Date of Lecture Link
17.10.2013 Video of Lecture 1
23.10.2013 Video of Lecture 2
24.10.2013 Video of Lecture 3
31.10.2013 Video of Lecture 4
06.11.2013 Video of Lecture 5
07.11.2013 Video of Lecture 6
13.11.2013 Video of Lecture 7
14.11.2013 Video of Lecture 8
20.11.2013 Video of Lecture 9
21.11.2013 Video of Lecture 10
27.11.2013 Video of Lecture 11
28.11.2013 Video of Lecture 12a, Video of Lecture 12b
11.12.2013 Video of Lecture 13
18. & 19.12.2013 Video of Lecture 14
08.01.2014 Video of Lecture 15
09.01.2014 Video of Lecture 16
16.01.2014 Video of Lecture 17
22.01.2014 Video of Lecture 18
23.01.2014 Video of Lecture 19
30.01.2014 Video of Lecture 20
Last edited 02.03.2017 19:21 by David Schubert