Lecture with Exercises: Correspondence Problems in Computer Vision

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

Winter Term 2018 / 2019
Lecture with Exercises (2+2SWS)
Language: English

Lecture: Thursday, 15:45 - 17:15, Computer Science Building, Seminar Room 0.108.
Theoretical Exercises: Friday, 11:30 - 13:00, Computer Science Building, Lecture Hall V38.02 (bi-weekly).
Programming Exercises: Friday, 11:30 - 13:00, Computer Science Building, VISGS Pool 0.452 (bi-weekly).


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.

Course Material

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

Lecture 01 18.10.2018 Introduction, Overview
No Assignment 19.10.2018 cancelled
Lecture 02 25.10.2018 Block Matching, Correlation Methods, Interest Points
Assignment 01 26.10.2018 Programming
No Lecture 01.11.2018 Public Holiday: All Saints
No Assignment 02.11.2018 cancelled
Lecture 03 08.11.2018 Optic Flow I: Local Differential Methods, Parametrisation Models
Assignment 02 09.11.2018 Theory
Lecture 04 15.11.2018 Optic Flow II: Global Differential Methods, Horn and Schunck
Assignment 03 16.11.2018 Programming
Lecture 05 22.11.2018 Optic Flow III: Advanced Constancy Assumptions, Large Motion
Assignment 04 23.11.2018 Theory
Lecture 06 29.11.2018 Optic Flow IV: Advanced Data and Smoothness Terms
Assignment 05 30.11.2018 Programming
Lecture 07 06.12.2018 Optic Flow V: High Accuracy Methods
No Assignment 07.12.2018 cancelled
Lecture 08 13.12.2018 Optic Flow VI: Advanced Numerics
Assignment 06 14.12.2018 Theory
Lecture 09 20.12.2018 Stereo Matching I: Projective and Epipolar Geometry
Assignment 07 21.12.2018 Programming
No Lecture 27.12.2018 Christmas Holidays
No Assignment 28.12.2018 Christmas Holidays
No Lecture 03.01.2019 Christmas Holidays
No Assignment 04.01.2019 Christmas Holidays
Lecture 10 10.01.2019 Stereo Matching II: Estimation of the Fundamental Matrix
Assignment 08 11.01.2019 Theory
Lecture 11 17.01.2019 Optic Flow + Stereo: Scene Flow Estimation
Assignment 09 18.01.2019 Programming
No Lecture 24.01.2019 cancelled
No Assignment 25.01.2019 cancelled
Lecture 12 31.01.2019 Medical Image Registration
Assignment 10 01.02.2019 Theory
Lecture 13 07.02.2019 Particle Image Velocimetry
Assignment 11 08.02.2019 Programming
Assignment 01 issued 19.10.2018 tutorial 26.10.2018
Assignment 02 issued 02.11.2018 tutorial 09.11.2018
Assignment 03 issued 09.11.2018 tutorial 16.11.2018
Assignment 04 issued 16.11.2018 tutorial 23.11.2018
Assignment 05 issued 23.11.2018 tutorial 30.11.2018
Assignment 06 issued 07.12.2018 tutorial 14.12.2018
Assignment 07 issued 14.12.2018 tutorial 21.12.2018
Assignment 08 issued 04.01.2019 tutorial 11.01.2019
Assignment 09 issued 11.01.2019 tutorial 18.01.2019
Assignment 10 issued 25.01.2019 tutorial 01.02.2019
Assignment 11 issued 01.02.2019 tutorial 08.02.2019


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