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

Technical University of Munich

Menu

Links



Computer Vision I: Variational Methods

WS 2016/17, TU München

Lecture

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.

Exercises

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

Retry Exam (Written)

Location: Room 5402.01.221K (CH 22210, Ivar-Ugi-Hörsaal)
Time and Date: Thursday, April 20, 2017, 16.00h-18.00h.

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

There will be a post-exam review (Klausureinsicht) for the retake exam on Friday, April 28, 2017 in our lecture room 02.09.023 at 10am. Please bring your student ID cards to identify yourselves.

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

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

Videos
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

Rechte Seite

Informatik IX
Computer Vision Group

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

Follow us on:

News

31.08.2022

Fulbright PULSE podcast on Prof. Cremers went online on Apple Podcasts and Spotify.

17.07.2022

MCML Kick-Off

On July 27th, we are organizing the Kick-Off of the Munich Center for Machine Learning in the Bavarian Academy of Sciences.

17.07.2022

AI Symposium

On July 22nd 2022, we are organizing a Symposium on AI within the Technology Forum of the Bavarian Academy of Sciences.

05.07.2022

We are organizing a workshop on Map-Based Localization for Autonomous Driving at ECCV 2022, Tel Aviv, Israel.

03.04.2022

In April 2022 Jürgen Sturm and Daniel Cremers were featured among the top 6 most influential scholars in robotics of the last decade.

More