ETH Zurich - D-INFK - IVC - CVG - Lectures - Computer Vision

Computer Vision

Professors:Marc Pollefeys, Siyu Tang, Fisher Yu
Teaching assistants: CVG: Mihai Dusmanu, Shaohui Liu, Songyou Peng, Fangjinhua Wang
VLG: Anpei Chen, Korrawe Karunratanakul, Shaofei Wang, Siwei Zhang
Lectures: Wed. 14:15-16:00 in NO C 60
Thu. 12:15-13:00 in HG G 5
Exercises: Thu. 13:15-14:00 in CAB G 51
Fri. 13:15-14:00 in CAB G 51


263-5902-00L Computer Vision

Computer Vision (following Tomaso Poggio, MIT): Computer Vision, formerly an almost esoteric corner of research and regarded as a field of research still in its infancy, has emerged to a key discipline in computer science. Vision companies have emerged and commercial applications become available, ranging from industrial inspection and measurements to security database search, surveillance, multimedia and computer interfaces. Computer Vision is still far from being a solved problem, and most exciting developments, discoveries and applications still lie ahead of us. Understanding the principles of vision has implications far beyond engineering, since visual perception is one of the key modules of human intelligence.

Important: course is managed through moodle

All the materials for lectures and exercises will be posted on moodle. You will also have to submit the exercises there. If you have questions, a forum is available. You can also ask private questions to TAs through the moodle system. Please, don't email questions unless it's very urgent.

Course Objectives

The objectives of this course are:
1.To introduce the fundamental problems of computer vision.
2.To introduce the main concepts and techniques used to solve those.
3.To enable participants to implement solutions for reasonably complex problems.
4.To enable participants to make sense of the computer vision literature.

Course Topics

Introduction and pinhole model, Feature extraction, Optical flow, Deep learning for CV: BP/MLP/CNN/RNN/Transformer/GCN, Image recognition (part-based models, BoW, sliding window, CNN-based), Image segmentation (k-means, Markov Random Fields, Graph Cuts, CNN-based), Object detection, Object tracking, Camera models and calibration, Multi-view geometry and SfM, Model fitting, Stereo and MVS

Target Audience

The target audience of this course are Master's Degree students who are interested to get a basic understanding of computer vision.


Fundamentals of calculus and linear algebra, basic concepts of algorithms and data structures, basic programming skills in Python.

Some useful links

The Computer Vision Homepage
Middlebury Stereo Vision Page
VLFeat SIFT package for MATLAB
Course Notes
Computer Vision: Algorithms and Applications


Q1: I am re-taking Computer Vision class. Can you transfer exercise grades from the previous time?
A: Please write directly to the TA responsible for the particular assignment INSTEAD of sending the assignment one more time. If the exercises did not change, the score will be transferred.
Q2: My code is correct, it just happens it does not run. Can you grade it?
A: No, please make sure it runs in other environment before sending. We will only grade working code.
Q3: My code is correct, but I did not write the report. Can you grade the assignment?
A: No, you should write the report.

© CVG, ETH Zürich webmaster: