Computer Vision II: Multiple View Geometry (IN2228)
SS 2018, TU München
- 18.04.18: No lecture on Tue, May 8 (Student General Meeting – Studentische Vollversammlung).
- 18.04.18: No lecture on Tue, May 1 (public holiday).
- 18.04.18: No lecture on Wed, April 25 (Student Body General Meeting – Fachschaftsvollversammlung). The tutorial takes place though!
- 04.04.18: Please consider installing Matlab on your laptop before the first tutorial (info below).
- 04.04.18: Tutorial starts on April 25.; due to room constraints the time and date is fixed to Wednesday 16:00 - 18:15.
- 03.04.18: First lecture is on Tuesday, April 17, 10:15 (no lectures/tutorial in week April 9.-13.).
- If you plan to attend, please register for the course in TUMonline.
- Later during the semester you will have to register for the exam.
Location: Room 02.09.023
Time and Date:
Tuesday 10:15 - 11:45
Wednesday 10:15 - 11:00 (optionally 10:15 - 11:45)
Lecturer: Prof. Dr. Daniel Cremers
Start: Tuesday, April 17, 2018
The lecture is held in English.
Location: Room 02.09.023 (optionally computer room 02.05.014 for practical part)
Time and Date: Wednesday 16:00 - 18:15
Organization: Nikolaus Demmel, Marvin Eisenberger
(If you have any questions please email to: email@example.com)
Start: Wednesday, April 25, 2018
Time and Date: Thursday, July 19, 2018, 10:30-12:30 (tentative)
There will be a retake exam at the end of the term break (probably in September).
If you cannot or don't want to use your own laptop for the Matlab programming exercises (second half of tutorial sessions), you can use the computer room 02.05.014. Ask Marvin or Nikolaus for login credentials during the tutorial session. They will be valid for the whole semester.
The computer room is specifically reserved for you during the Wednesday tutorial slot 16:00 - 18:15, but you can use it at any other time, when there are free computers.
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. You may use the lab computers with MATLAB pre-installed. If you want to use your own laptop, please bring it to the exercise sessions. You may install MATLAB 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.
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.
You can find recordings of a previous iteration of this course on Youtube.
Yi Ma, Stefano Soatto, Jana Kosecka, Shankar S. Sastry. An Invitation to 3-D Vision