TSBB33 3D Computer Vision
This course covers the algorithms and estimation problems used to infer 3D structure from images. The course covers both the mathematics used, and how these are put into practice in algorithm implementation. The course features two computer labs, and a 3hp project where groups of participants together will implement a structure from motion system. The project is presented both in written form and orally at a seminar. The course ends with a written exam on the theoretical content.
General Information
- Course syllabus
Course syllabus can be found in the Study guide.
- Schedule
The course schedule in TimeEdit.
- Literature
- K. Nordberg, Introduction to Representations and Estimation in Geometry (IREG). [Book webpage]
- R. Szeliski, Computer Vision, Algorithms and Applications (CVAA).
Available as an on-campus e-book via the LiU library. [Book webpage] - R. Hartley and A. Zisserman, Multiple View Geometry in Computer Vision (HZ), on-campus e-book
- Additional material can be found in the course repository.
- Another recent book that may interest you (we will not use this
one in the course):
K. Ikeuchi, Computer Vision, a Reference Guide, on-campus e-book.
Lecture Schedule VT2024
Below is an up-to-date list of all staffed lectures and computer labs.
Additional, unstaffed computer lab time can be found in TimeEdit.All lectures are given in Systemet and all labs are in Olympen, both located at the Department of Electrical Engineering.
Date,Time,Room Activity Teacher Literature March 25: 10.15-12
Systemet
Lecture 1
Introduction, 3D perception, local features
Per-Erik Forssén CVAA: 7.1
Background geometry: IREG ch. 7-9,13March 26: 13.15-15
Systemet
Lecture 2 </td>
Maximum likelihood, RANSAC, cameras and epipolar geometryMårten Wadenbäck Multi-dim course, first half. Also IREG: 17.3 (RANSAC). April 2: 13.15-15
Systemet
Lecture 3
Cost minimisation, and robust error norms
Per-Erik Forssén K. Madsen, NL Least Squares Tutorial
Z. Zhang, Parameter Est. Techniques, Ch. 9.April 9: 13.15-17.00
Olympen
CE1
Non-linear optimization and gold standard
Johan Edstedt
Ioannis AthanasiadisCE1 Lab sheet April 12: 15.15-17
Systemet
Lecture 4
Multiview stereo, correspondence fields, and triangulation
Per-Erik Forssén Furukawa MVS-tutorial, PatchMatch paper
IREG: 10.4, CVAA: 12.1, 12.3
Jump Flooding paperApril 15: 10.15-12
Systemet
Lecture 5
Representation of 3D rotations
Mårten Wadenbäck IREG: ch. 11 April 22: 10.15-12
Systemet
Lecture 6
Absolute and relative camera pose, and minimal cases
Mårten Wadenbäck CVAA: 8.1.5, 11.2
IREG: ch. 15April 23: 13.15-17
Olympen
CE2
Dense Correspondences with PatchMatch
Johan Edstedt
Ioannis AthanasiadisCE2 Lab sheet
Skeleton code
Cheatsheet notebookApril 25: 8.15-10
Systemet
Lecture 7
Structure from motion, bundle adjustment, and project start
Per-Erik Forssén IREG: 15.1,15.12 (3D alignment), 21 (SfM)
CVAA: 8.1.5, 8.3.1 (3D alignment), 11 (SfM)May 7: 13.15-15
Systemet
Guest Lecture 1
Maxar Sweden
Amanda Berg May 13: 10.15-12
Systemet
Guest Lecture 2
IMG Arena
David Habrman May 21: 13.15-17
Systemet
Final Seminar
Project presentations, exam discussion, and wrap up
Per-Erik Forssén 3D reconstruction project
Half the course consists of a 3D reconstruction project. The project starts on April 25, and ends with a final seminar on May 21. The project builds on top of the two computer exercises.
For more information see the project description page.