Computer vision

CS-442

Media

CS-442 Computer vision

Modeling People and their Clothes

26.05.2025, 15:10

CS-442 Computer Vision | Spring 25

26.05.2025, 15:38

Shape from Motion

19.05.2025, 15:10

CS-442 Computer Vision | Spring 25

19.05.2025, 15:38

Shape from Contour

12.05.2025, 15:32

CS-442 Computer Vision | Spring 25

12.05.2025, 15:38

Shape from Stereo

05.05.2025, 15:33

CS-442 Computer Vision | Spring 25

05.05.2025, 15:39

Shape from X

28.04.2025, 15:10

CS-442 Computer Vision | Spring 25

28.04.2025, 15:38

CS-442 Computer Vision | Spring 25

21.04.2025, 15:32

CS-442 Computer Vision | Spring 25

21.04.2025, 15:35

Shape from Shading and Texture

14.04.2025, 15:32

CS-442 Computer Vision | Spring 25

14.04.2025, 15:38

Delineation2

24.03.2025, 15:34

CS-442 Computer Vision | Spring 25

24.03.2025, 15:41

Delineation

17.03.2025, 15:11

CS-442 Computer Vision | Spring 25

17.03.2025, 15:39

Deep Learning

10.03.2025, 15:11

CS-442 Computer Vision | Spring 25

10.03.2025, 15:39

Introduction and Human Vision

17.02.2025, 15:12

CS-442 Computer Vision | Spring 25

17.02.2025, 15:40

CS-442 Summer 2024

27.05.2024, 15:39

CS-442 Summer 2024

13.05.2024, 15:32

CS-442 Summer 2024

13.05.2024, 15:40

Nerfs + Shape from Contours

06.05.2024, 15:32

CS-442 Summer 2024

06.05.2024, 15:39

Stereo

29.04.2024, 15:11

CS-442 Summer 2024

29.04.2024, 15:38

Shape from Shading

22.04.2024, 15:11

CS-442 Summer 2024

22.04.2024, 15:39

CS-442 Computer Vision | Spring 25

07.04.2025, 15:38

Texture

15.04.2024, 15:10

CS-442 Summer 2024

15.04.2024, 15:38

CS-442 Computer Vision | Spring 25

31.03.2025, 15:39

Segmentation

08.04.2024, 15:36

CS-442 Summer 2024

08.04.2024, 15:44

Delineation II

25.03.2024, 15:34

CS-442 Summer 2024

25.03.2024, 15:40

Delineation I

18.03.2024, 15:33

CS-442 Summer 2024

18.03.2024, 15:39

Deep Nets

11.03.2024, 15:11

CS-442 Summer 2024

11.03.2024, 15:39

CS-442 Computer Vision | Spring 25

03.03.2025, 15:38

Edge Detection

04.03.2024, 15:33

CS-442 Summer 2024

04.03.2024, 15:39

CS-442 Computer Vision | Spring 25

24.02.2025, 15:39

Image Formation

26.02.2024, 15:10

CS-442 Summer 2024

26.02.2024, 15:38

20, Recap

02.06.2021, 13:02

19, Shape from Contours

02.06.2021, 12:58

18, Shape From Stereo-2

18.05.2021, 10:37

17, Shape from Stereo-1

12.05.2021, 15:21

16, Shape from Texture

12.05.2021, 15:20

15, Shape from Shading and Texture

04.05.2021, 21:01

14, Texture

27.04.2021, 16:43

13, Segmentation - 2

27.04.2021, 15:34

12, Segmentation - 1

23.04.2021, 10:14

11, Delineation - 2

23.04.2021, 10:13

10, Delineation - 1

23.04.2021, 10:13

9, Edge Detection - 4

23.04.2021, 10:09

8, Edge Detection - 3

23.04.2021, 10:08

7, Edge Detection - 2

23.04.2021, 10:07

6, Edge Detection - 1

23.04.2021, 10:06

5, From World to Images - 4

23.04.2021, 10:05

4, From World to Images - 3

23.04.2021, 10:04

3, From World to Images - 2

23.04.2021, 10:04

2, From World to Images - 1

23.04.2021, 10:03

1, Introduction to the Class

23.04.2021, 10:03

This file is part of the content downloaded from Computer vision.

Course summary

Welcome to the Computer Vision class!

Computer Vision is the branch of Computer Science whose goal is to model the real world or to recognize objects from digital images. These images can be acquired using still and video cameras, infrared cameras, radars, or specialized sensors such as those used in the medical field.

The students will be introduced to the basic techniques of the field of Computer Vision. They will learn to apply Image Processing techniques where appropriate.

We will concentrate on the black and white and color images acquired using standard video cameras. We will introduce basic processing techniques, such as edge detection, segmentation, texture characterization, and shape recognition.

Instructor

Prof. Pascal Fua
Computer Vision Laboratory (CVLAB)
BC 310
E-mail: pascal.fua@epfl.ch

Course Times and Locations

Lectures: Monday 13:15 - 15:00 CM13

Exercises: Tuesday 10:15 - 12:00 every other week. INM 200 (A-M), INM 202 (N-Z)

Please check the course schedule and bring your own laptops for the exercise sessions.

Questions

If you have any questions please post them in the discussion forum and we will answer you.

Contact TAs

Chen Zhao (chen.zhao@epfl.ch)

Aoxiang Fan (aoxiang.fan@epfl.ch)

Corentin Dumery (corentin.dumery@epfl.ch)

Deniz Mercadier (deniz.mercadier@epfl.ch)

Yingxuan You (yingxuan.you@epfl.ch)

Zhantao Deng (zhantao.deng@epfl.ch)

Graded Exercise Sessions

We will grade two of the exercise sessions. They will count for 10% of you final grade each. There will be around two hours for you to implement some algorithms. You must join the graded exercise sessions in person, otherwise you will lose the points.

Recorded Lectures

The lectures will be recorded and deposited on this channel.

Final exam

It will be a 90min closed book exam with multiple-choice and open-ended questions. You will be allowed ONE double-sided hand-written (non-digital, non printed) A4 page of notes. It will count for 80% of your final grade.

Course Schedule

17-02-2025

Course

24-02-2025

Course

25-02-2025

Exercise Session 1

03-03-2025

Course

10-03-2025

Course

11-03-2025

Exercise Session 2

17-03-2025

Course

24-03-2025

Course

25-03-2025

Exercise Session 3 (Cancelled grading)

31-03-2025

Course

07-04-2025

Course

08-04-2025

Exercise Session 4 GRADED

14-04-2025

Course

28-04-2025

Course

29-04-2025

Exercise Session 5

05-05-2025

Course

12-05-2025

Course

13-05-2025

Exercise Session 6 GRADED

19-05-2025

Course

20-05-2025

Exercise Session 7

Graded Exercise 1

Reference Text Books

R. Szeliki, Computer Vision: Computer Vision: Algorithms and Applications, 2021.

R. Hartley and A. Zisserman, Multiple View Geometry in Computer Vision, Cambridge University Press, 2003.

Introduction to the Class

From World to Images

Edge Detection

Edge definition, edge operators, Canny edge detector, and machine-learning based detectors.

Delineation

Going from edge elements to complete outlines.

Segmentation

Partitioning images into separate regions of interest.

Texture

Texture: What is it and how can it be characterized and analyzed.

Course Evaluation

Even though there will be no official I&C evaluation this semester, I would like some feedback on this class. I would therefore ask you to fill this questionnaire that mirrors the standard one. You answers will be totally anonymous as usual.