Home
Uni-Logo
 

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 Python, where you will learn to implement and/or test the most important techniques presented in the lectures.

Lecture:
(2 SWS)		 Tuesday, 10:15-11:45,
Room: 101-01-016/18
Exercises:
(2 SWS)

 Thursday, 16:00-18:00 (first session Oct. 26),
Room: 101-01-016/18
Contact persons: Phillip Schröppel, Simon Ging
Please ask questions via ILIAS Forum instead of contacting us directly.
You can also find the exercise session schedule on ILIAS.
Beginning: Tuesday, October 17, 2023
ECTS Credits: 6
Requirements: Fundamental mathematical knowledge and programming skills in Python. 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.
Language: The lectures are given in English.
Exam: You can have a look at your exam on 18.4. 13:30-14:00 in 52-1-33. Please bring an ID.

Motion Segmentation

Material:

Lecture material will be updated during the course. Recording files are about 200MB each.

Class 1 (17.10.): Introduction Recordings
Class 2 (24.10.)*: Diffusion filters, TV minimization Recordings
Class 3 (31.10.): Spectral clustering Recordings
Class 4 (7.11.): Deep learning Recordings
Class 5 (14.11.): Object detection and semantic segmentation Recordings
Class 6 (21.11.): Optical Flow Recordings
Class 7 (28.11.): Deep learning based optical flow Recordings
Class 8 (5.12.): Video segmentation Recordings
Class 9 (12.12.): 3D geometry and camera calibration Recordings
Class 10 (19.12.): Stereo reconstruction Recordings
Class 11 (9.1.): Disparity estimation and scene flow Recordings
Class 12 (16.1.): Structure from motion Recordings
Class 13 (23.1.): Deep learning based 3D vision Recordings
Class 14 (30.1.): Image generation Recordings
Class 15 (6.2.): Next generation deep learning Recordings

Exercise material:

Short introduction to git
Setup instructions
Exercises on github

NumPy quickstart
PyTorch cheat sheet
PyTorch for NumPy users