This is an old revision of the document!
Computer Vision II: Multiple View Geometry (IN2228)
SS 2019, TU München
News
- July 24, 2019: Q&A session during the tutorial, no additional exercise sheet.
Please prepare questions beforehand and email them to mvg-ss19@vision.in.tum.de - June 6, 2019: There has been a minor change in the formulation of exercise 1b,c on Sheet 4, Part II to make it consistent with Part I.
Registration
If you plan to attend, please register for the course in TUMonline.
Later during the semester you will have to register for the exam.
Lecture
Time and Location:
Wednesday 12:30 - 14:00, Interims Hörsaal 2 (5620.01.102)
Thursday 11:15 - 12:00, MI Hörsaal 1 (5602.EG.001)
Lecturer: Prof. Dr. Daniel Cremers
Start: Thursday, May 2, 2019
The lecture is held in English.
Exam
Date: Wednesday, August 14, 2019, 10:30 - 12:30
No cheat sheet allowed.
Exercises
Location: Interims Hörsaal 2 (5620.01.102)
Time: Wednesday, 16:00 - 18:15
Organization: Mohammed Brahimi, David Schubert
(If you have any questions please email to: mvg-ss19@vision.in.tum.de)
Start: Wednesday, May 15, 2019
Exercises are split into a theoretical and a practical part. Due to the high number of students, the practical part of the tutorial will also take place in the Interims Hörsaal, which requires students to bring a laptop. If this is not possible, students can also use the computers in room 02.05.014, which is reserved during the tutorial, but can be used at any other time if there are free computers. Don't forget to get login credentials from the tutors in case you are planning to do so.
MATLAB
The programming exercises are done in MATLAB. You don't need extensive prior MATLAB knowledge. If you have never used MATLAB before, we recommend following a basic tutorial. Please install MATLAB on your laptop before the first exercise using the university's student licenses.
- MATLAB cheatsheet: http://web.mit.edu/18.06/www/Spring09/matlab-cheatsheet.pdf
- MATLAB on your own computer: http://matlab.rbg.tum.de
- We don't use much beyond core MATLAB functionality. You may need the Image Processing Toolbox for reading and displaying images.
Note on MATLAB version:
We suggest you to use a MATLAB version 2016b or later. For the solutions we make use of function definitions inside Matlab script files. This feature was added only in 2016b. So if you have an earlier version, we suggest you to upgrade (alternatively you can move all function definitions to separate files). See also https://de.mathworks.com/help/matlab/matlab_prog/local-functions-in-scripts.html.
Summary
The lecture introduces the basic concepts of image formation - perspective projection and camera motion. The goal is to reconstruct the three-dimensional world and the camera motion from multiple images. To this end, one determines correspondences between points in various images and respective constraints that allow to compute motion and 3D structure. A particular emphasis of the lecture is on mathematical descriptions of rigid body motion and of perspective projection. For estimating camera motion and 3D geometry we will make use of both spectral methods and methods of nonlinear optimization.
Lecture Material
Slides and exercises can be downloaded here. We will provide the password in the tutorial sessions. Alternatively, for password requests, please contact us using your TUM email address.
Lecture Videos
You can find recordings of a previous iteration of this course on Youtube.
Literature
Yi Ma, Stefano Soatto, Jana Kosecka, Shankar S. Sastry. An Invitation to 3-D Vision