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++, you can use Python on your own risk if you prefer), where you will learn to implement the most important techniques presented in the lectures. The lecture will be provided as online course. There is recorded class material, which will be augmented by a weekly online meeting in Zoom, which provides additional updates (the state of the art is changing rapidly) and allows you to ask questions about the material. Be aware that the online meetings will not be recorded. The exercises will be also handled online via an online forum, where you can seek the help of staff members and other students. Lecture: (2 SWS) Wednesday, 10:30-11:30, Room: Online meeting Exercises: (2 SWS) via forum Contact persons: Tonmoy Saikia, Osama Makansi Beginning: Wednesday, November 4, 2020 ECTS Credits: 6 Recommended semester:   2 or 3 (Master) Requirements: Fundamental mathematical knowledge and programming skills in C++ (or Python on your own risk). Image Processing and Computer Graphics teaches important technical knowledge that won't be repeated in Computer Vision. Thus, prior attendance of Image Processing is highly recommended. The online meetings will NOT be recorded. You can pass the exam with only the material from the available recordings, but you will miss up-to-date information. Language and exam: The lectures are given in English.

---

Class recordings:

Files are about 200MB each.

Class 1: Introduction
Class 2: Diffusion filters, TV minimization
Class 3: Image segmentation and combinatorial optimization
Class 4: Deep learning I
Class 5: Spectral clustering
Class 6: Deep learning II
Class 7: Optical Flow I
Class 8: Optical Flow II
Class 9: Video segmentation(optional due to the shorter semester)
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

---

Slides:

Class 1: Introduction
Class 2: Diffusion filters, TV minimization
Class 3: Image segmentation and combinatorial optimization
Class 4: Spectral clustering
Class 5: Deep learning I
Class 6: Deep learning II
Class 7: Optical Flow I
Class 8: Optical Flow II
Class 9: Video segmentation (optional due to the shorter semester)
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
Exercise 2
Exercise 3 (~280MB)
Exercise 4
Exercise 5
Exercise 6
Exercise 7

---