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

Technical University of Munich

Menu
Home Teaching Winter Semester 2018/19 Computer Vision I: Variational Methods

Computer Vision I: Variational Methods

WS 2018/19, TU München

News

08.11.18:

  • On Tuesday, 13.11.18 the lecture is canceled because of yet another Tum assembly (SVV).

24.10.18:

  • Due to a Tum assembly (FVV) the exercise on Wednesday, 31.10.18 is canceled.

17.10.18:

  • The lecture on Thursday, 25.10.18 is canceled because the Interims Hörsaal 2 is occupied.

16.10.18:

  • Due to an exceptionally high number of participants we moved the lecture to a bigger room, namely the Interims Hörsaal 2.

14.10.18:

  • There won't be any lectures in the first week of the semester. Classes will start on Tuesday Oct 23rd.
Lecture

Location: Interims Hörsaal 2 (5620.01.102)
Time and Date:
Tuesday, 10.15h - 11.45h
Thursday, 10.15h - 11.00h
Lecturer: Prof. Dr. Daniel Cremers

The lectures are held in English.

Exercises

Location: Interims II (at the chemistry building): 004, Hörsaal 1 (5416.01.004)
Time and Date: Wednesday, 10.30h - 12.30h
Organization: Marvin Eisenberger, Mohammed Brahimi
Contact: cvvm-ws18@vision.in.tum.de

Summary

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.

Prerequisites

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

Slides and exercise sheets can be accessed here.
For password request, please contact us using your TUM email address.

Videos

A previous (very similar) version of this course was recorded in 2013. The videos can be found on Youtube.

Rechte Seite

Informatik IX
Chair for Computer Vision & Artificial Intelligence

Boltzmannstrasse 3
85748 Garching

info@vision.in.tum.de