Computer Vision

Prof. Thomas Brox

Computer vision is a very active research field with many practical applications, for instance in quality control, robotics, driver assistance systems, and many more. The ultimate goal of computer vision is to imitate the great capabilies of the human visual system, allowing the computer not only to record images but also to interpret them. Significant progress has been made in recent years. This course introduces the most important concepts in today's Computer Vision research. The exercises will consist of programming assignments (in C/C++), where you will learn to implement the most important techniques presented in the lectures. Lecture: (2 SWS) Wednesday, 10-12, Room: SR 02-017, Building 52 Exercises: (2 SWS) Thursday, 14-16, Room: SR 00-029, Building 082 Contact persons: Anton Böhm, Osama Makansi Beginning: Wednesday, October 30, 2019 ECTS Credits: 6 Recommended semester:   2 or 3 (Master) Requirements: Fundamental mathematical knowledge and programming skills in C++. Image Processing and Computer Graphics teaches important technical knowledge that won't be repeated in Computer Vision. Thus, prior or parallel attendance of Image Processing is highly recommended. Language and exam: The lectures are given in English.

---

Slides:

Slides are from last year and get updated during the course.

Class 1 (30.10.): Introduction
Class 2 (6.11.): Diffusion filters, TV minimization
Class 3 (13.11.): Deep learning I
Class 4 (20.11.): Image segmentation and combinatorial optimization
Class 5 (27.11.): Spectral clustering
Class 6 (4.12.): Deep learning II
Class 7 (11.12.): Optical Flow I
Class 8 (18.12.): Optical Flow II
Class 9 (8.1.): Video segmentation
Class 10 (15.1.): 3D geometry and camera calibration
Class 11 (22.1.): Stereo reconstruction
Class 12 (29.1.): Disparity estimation and scene flow
Class 13 (5.2.): Structure from motion
Class 14 (12.2.): Deep learning III (and Q&A)

---

Class recordings:

Files are about 200MB each. Recordings are from last year and get updated during the course.

Class 1: Introduction
Class 2: Diffusion filters, TV minimization
Class 3: Deep learning I
Class 4: Image segmentation and combinatorial optimization
Class 5: Spectral clustering
Class 6: Deep learning II
Class 7: Optical Flow I
Class 8: Optical Flow II
Class 9: Video segmentation
Class 10: 3D geometry and camera calibration
Class 11: Stereo reconstruction
Class 12: Disparity estimation and scene flow
Class 13: Structure from motion
Class 14: Deep learning III

---

Exercise material:

Exercise 1: 7.11.
Exercise 2: 14.11. (~280MB)
Exercise 3: 21.11.
Exercise 4: (28.11.) Catch up with the previous assignments
Exercise 5: (5.12.) Catch up with the previous assignments.
Exercise 6: 12.12.
Exercise 7: (19.12.) Catch up with the previous assignments.
Exercise 8: (9.1.) Catch up with the previous assignments.
Exercise 9: 16.1.
Exercise 10: 23.1.
Exercise 11: 30.1.
Exercise 12: (6.2.) Catch up with the previous assignments.
Exercise 13: (13.2.) Catch up with the previous assignments.

---