Lecture and Exercises: Correspondence Problems in Computer Vision

Lecturer: Prof. Andres Bruhn
Coordinator of Tutorials: Andres Bruhn

Summer Term 2020
Lecture with Exercises (2+2SWS)
Language: English

Lecture: Wednesday, 15:45 - 17:15, Computer Science Building, Lecture Hall V38.03.
Theoretical Exercises: Tuesday, 09:45 - 11:15, Computer Science Building, Seminar Room 0.108 (bi-weekly).
Programming Exercises: Tuesday, 09:45 - 11:15, Computer Science Building, VISGS Pool 0.452 (bi-weekly).

Please note that the slot for lectures and tutorials have been switched!

The lecture will be recorded via OpenCast. Apart from the traditional course material, also the recordings will be available in ILIAS.

Since, currently, classroom exercises are not allowed, the assignments have to be done before the corresponding tutorials at home (and not live with the lecturer during the corresponding tutorials - as usual). In the tutorials that will take place each week via WebEx, you can then ask questions regarding parts of the assignment that you were not able to solve. Of course, you can also ask questions in the ILIAS discussion forum at any time. As in previous years, there will be no correction of the assignments but example solutions will be uploaded in ILIAS.

Please note that, in case you prefer classroom exercises, the lecture will be offered again in the winter semester.

Correspondence problems are a central topic in computer vision. The basic task amounts to identifying and matching corresponding features in different images or views of the same scene. Typical examples for correspondence problems are (i) the estimation of motion information from consecutive frames of an image sequence (optic flow), (ii) the reconstruction of a 3-D scene from a stereo image pair, (iii) the registration of medical image data from different image acquisition devices (e.g. CT and MRT), and (iv) the analysis of the motion of fluid flows. The central part of this lecture is concerned with discussing the most important types of correspondence problems together with suitable models and algorithms for solving them.

This class requires undergraduate knowledge in mathematics (e.g. "Mathematik für Informatiker und Softwaretechniker"). Knowledge in image processing or computer vision is useful as well. Also basic knowledge in artificial intelligence can be helpful. The lectures will be given in English.

This class is particularly suited for those students who wish to pursue a master thesis in the CVIS group in the field of computer vision.

All course material (lecture notes, assignments, code, example solutions) are available in the ILIAS system.


Lecture 01 22.04.2020 Introduction, Overview
No Assignment 28.04.2020 cancelled
Lecture 02 29.04.2020 Block Matching, Correlation Methods, Interest Points
Assignment 01 05.05.2020 Programming
Lecture 03 06.05.2020 Optic Flow I: Local Differential Methods, Parametrisation Models
Assignment 02 12.05.2020 Theory
Lecture 04 13.05.2020 Optic Flow II: Global Differential Methods, Horn and Schunck
Assignment 03 19.05.2020 Programming
Lecture 05 20.05.2020 Optic Flow III: Advanced Constancy Assumptions, Large Motion
Assignment 04 26.05.2020 Theory
Lecture 06 27.05.2020 Optic Flow IV: Advanced Data and Smoothness Terms
No Lecture 02.06.2020 Pentecost Holidays
No Assignment 03.06.2020 Pentecost Holidays
Assignment 05 09.06.2020 Programming
Lecture 07 10.06.2020 Optic Flow V: High Accuracy Methods, SOR
Assignment 06 16.06.2020 Theory
Lecture 09 17.06.2020 Stereo Matching I: Projective and Epipolar Geometry
Assignment 07 23.06.2020 Programming
Lecture 10 24.06.2020 Stereo Matching II: Estimation of the Fundamental Matrix
Assignment 08 30.06.2020 Theory
Lecture 11 01.07.2020 Optic Flow + Stereo: Scene Flow Estimation
Assignment 09 07.07.2020 Programming
Lecture 12 08.07.2020 Medical Image Registration
Assignment 10
14.07.2020 Theory
Lecture 13 15.07.2020 Particle Image Velocimetry


Lecture 08 Optic Flow VI: Advanced Numerics
Assignment 11 Programming


Assignment 01 issued 28.04.2020 tutorial 05.05.2020
Assignment 02 issued 05.05.2020 tutorial 12.05.2020
Assignment 03 issued 12.05.2020 tutorial 19.05.2020
Assignment 04 issued 19.05.2020 tutorial 26.05.2020
Assignment 05 issued 02.06.2020 tutorial 09.06.2020
Assignment 06 issued 09.06.2020 tutorial 16.06.2020
Assignment 07 issued 16.06.2020 tutorial 23.06.2020
Assignment 08 issued 23.06.2020 tutorial 30.06.2020
Assignment 09 issued 30.06.2020 tutorial 07.07.2020
Assignment 10 issued 07.07.2020 tutorial 14.07.2020

Link to "Correspondence Problems in Computer Vision" in the Campus system (Lecture)
Link to "Correspondence Problems in Computer Vision" in the Campus system (Exercise)
Link to "Correspondence Problems in Computer Vision" in ILIAS

Zum Seitenanfang