Computer Vision course, Info UAIC, Spring 2026

Computer Vision (taught in English, Spring 2026)

(latest update: 2026/02/16

On this page is all relevant information regarding the Computer Vision course, aka CV, taught by Prof.Dr. Radu Timofte (English classes) in the Spring semester of 2026.
The laboratory assistant is Drd. Andrei Arhire (email: andreiarhire2708 [at] gmail.com)

For questions related to the English classes please preferably use the Discord and the email: radu.timofte [at] uni-wuerzburg.de

Contents

This course aims at offering a self-contained account of computer vision and its underlying concepts, including the recent use of deep learning.

The topics that will be covered are:

introduction to computer vision
sampling and quantization
image enhancement
feature description
feature detection
geometry and detection
motion and tracking
traditional object recognition
deep learning
generative methods
applications

Objectives

Overview of the most important concepts of image formation, perception and analysis, and Computer Vision.
Gaining own experience through home assignments, practical computer and programming exercises.

Prerequisites

Basic concepts of mathematical analysis and linear algebra.
Basic concepts of physics and optics.
The computer exercises are based on Python, PyTorch and TensorFlow.
The course language is English.

Locations

The lectures will take place online, on Saturdays in the Spring Semester in five sessions. To attend please use the the Zoom video conference link.
The laboratories will take place in-person, on Tuesdays, 08:00-10:00 (IAO1, room C411) and 12:00-14:00 (ISS1, room C401), Thursdays (SAI1 , room C403)in the Spring Semester, weekly.

Scheduled lectures and exam date:

Join Discord Computer Vision server using the invite: https://discord.gg/S6AeJM9m

Lectures 0, 1, 2, 3, 3x (0 and 3x are not for exam) on February 21 from 9:00 to 15:00, online Zoom
Lectures 4, 5, 6, 6x (6x is not for exam) on March 7 from 9:00 to 15:00, online Zoom
Lectures 7, 8, 9 on March 28 from 9:00 to 15:00, online Zoom
Lectures 10, 11, 12 on April 25 from 9:00 to 15:00, online Zoom
Lectures 13, 14 on May 16 from 9:00 to 13:00, online Zoom
Colloquium (Exam) on June 6, 9:00 to 11:00 , written, closed-book, in-person, room C2
Re-Exam on June 27, 9:00 to 11:00 , written, closed-book, in-person, room C309

Laboratories / Exercise sessions

Join Discord Computer Vision server using the invite: https://discord.gg/S6AeJM9m

Info schedule for laboratories

Home Assignments

For those willing to exercise and prepare for the exam there are provided 4 Home Assignments with 8 tasks each.
These Home Assignments are optional, not graded, and meant only to familiarize with the kind of tasks the final written exam will have.

Grading

The grading of Computer Vision (taught in English) is as follows:

The final CV (Eng) grade (maximum 10) is composed from: 40% - exercise sessions (laboratories), 60% - colloquium/exam (mandatory). To pass this class the exam is mandatory
Optional: project covering Computer Vision course topics can be used either to augment or to replace the exam grade. The exam is still mandatory. Teams composed of one up to three students can work together for a project. The details will be provided by the lab assistant.

Course materials, required contents for exam

For exam the students are required to prepare the contents covered during the lectures, exercise sessions, home assignments and found on the provided slides and lab materials. Examples of potential exam topics are found in the home assignments.
Supplementary materials and lecture slides will be provided after each lectures session.

Re-Exam (TBU)

Info UAIC students should register for the optional re-exam (and provide their details and contact email) by filling out the form.

Exam/Colloquium (TBU)

ALL the students from Info UAIC should register for the exam (and provide their details and contact email) by June 4th by filling out the form.

What?
The exam for Computer Vision will take place in-person on June 6, 9:00-11:00, in room C2 (TBU), Faculty of Computer Science. The exam is closed-book, written, in-person. The students are not allowed to bring/use any hardcopies, books, slides, prints, (hand)written contents on paper. The students are not allowed with electronic materials, electronic devices, Internet. The exam is individual, each student should work alone on their exam tasks.

Who?
ALL enrolled students in this class are invited to take the exam regardless the status of their Home Assignments, Laboratories or Projects. Note that the exam is mandatory for all students in order to pass this class.

How?
The students will receive their quizzes before 9:00 and should provide their on paper, written solutions no later than 11:00
Exam Protocol

June 6th 8:50 : ALL enrolled students will be required to be in-person present in room C2.
June 6th 8:55 : Each student will receive her/his personalized test with tasks similar to those from the Home Assignments.
June 6th 9:00 : The exam starts.
June 6th 9:00 - 11:00 : ALL enrolled students will be required to remain in room C2 and work on their exam tasks.
June 6th 11:00 : The exam is over. The students are invited to provide their written, on paper, solutions. Their full names and master program information should be on their front page of their written solutions.

Results
The exam results will be provided together with the final grades and the partial points obtained from laboratory, home assignments and projects (if any). Note that the final grade is composed of 40% laboratory, 60% exam and the bonus points. The exam is mandatory for ALL. The grade from optional projects (if any) will replace or augment the exam grade.

Updates
All the updates related to the exam will be provided on the course page.

Plagiarism and misconduct

Plagiarism and misconduct are not tolerated!
Any overlap in contents (text, media, codes, solutions) between different sources (e.g., two students, one student vs. Internet, etc.) will be carefully checked and the corresponding students will be disqualified (will not pass this class and an administrative action will be open).
It is OK to use other resources to support your answers, solutions, exercise solutions, projects, homework. However, those resources should be properly cited/references and the used contents correctly marked/identified. The extra, own contribution should be made clear.
If a student is not able to defend his work, is not knowledgeable enough on the contents (especially the own contributions) of his work provided in this course (as text, media, codes, solutions, project results, answers, etc.), then that student will be suspected of appropriation of work and misconduct and can be disqualified (will not pass this class and an administrative action will be open).

Bibliography

Gonzales and Woods, Digital Image Processing, Pearson, 2018
Szeliski, Computer Vision: Algorithms and Applications, Springer, 2010 (online draft)
Hartley and Zisserman, Multiple View Geometry in Computer Vision, Cambridge University Press, 2004
Forsyth and Ponce, Computer Vision: A Modern Approach, Prentice Hall, 2002
Palmer, Vision Science, MIT Press, 1999
Goodfellow, Bengio, Courville, Deep Learning, MIT Press, 2016
Mitchell, Machine Learning, McGraw-Hill, 1997
Duda, Hart and Stork, Pattern Classification (2nd Edition), Wiley-Interscience, 2000
Sutton & Barto, On-line book. The classic reference to the field of reinforcement learning.
Bansai, Kadambi, Raskar, Computational Imaging Book , 2022
Torralba, Isola, Freeman, Foundations of Computer Vision , 2024