Subject description - BE4M33MPV

Summary of Study | Summary of Branches | All Subject Groups | All Subjects | List of Roles | Explanatory Notes               Instructions
BE4M33MPV Computer Vision Methods
Roles:PO, PV, PS, P Extent of teaching:2P+2C
Department:13133 Language of teaching:EN
Guarantors:Matas J. Completion:Z,ZK
Lecturers:Čech J., Matas J., Mishkin D., Sattler T., Tolias G. Credits:6
Tutors:Too many persons Semester:L

Web page:

https://cw.fel.cvut.cz/wiki/courses/mpv/start

Anotation:

The course covers core computer vision problems: search for correspondences between images, 3D reconstruction, object detection, recognition, segmentation of objects in images and videos, image retrieval from large databases and tracking of objects in video sequences. In the labs, the students implement selected methods and test performance on real-world problems. This course is also part of the inter-university programme prg.ai Minor. It pools the best of AI education in Prague to provide students with a deeper and broader insight into the field of artificial intelligence. More information is available at https://prg.ai/minor.

Study targets:

The methods for image registration, retrieval and for object detection and tracking are explained. In the labs, the students implement selected methods and test performance on real-world problems.

Course outlines:

1. Correspondences and wide baseline stereo I. Motivation and applications. Perspective pinhole camera model.
Interest point and distinguished regions detection: Harris detector (corner detection)
2. Correspondences and wide baseline stereo II. Laplace operator and its approximation by difference of Gaussians. Affine covariant version. Descriptors of SIFT (scale invariant feature transform), RootSIFT.
Multiview feature matching. Deep learned features: R2D2, Super Glue.
3. RANSAC (Random Sample and Consensus)
4. 3D reconstruction I.
5. 3D reconstruction II
6. Deep learning I. Convolutional Neural Networks, Transformers. Architectures for image recognition.
7. Deep learning II. Architectures for object detection and semantic segmentation.. Foundation models (CLIP, DINO, Segment Anything, Depth Anything)
8. Tracking I. Problem formulation. KLT - Lucas-Kanade tracker, DCF - discriminative correlation tracker.
9. Tracking II. Long-term tracking.
10. Image Retrieval I., Bag-of-Words, VLAD, spatial verification, special objectives: zoom in/out .
11. Image Retrieval II. deep metric learning, architectures, losses
12. Self-supervised representation learning. Auto-encoders, learning via augmentations, contrastive approaches
13. Generative modelling for Computer Vision

Exercises outline:

1. Introduction to Image Processing in python using PyTorch.
2. Debugging pytorch.
3. Correspondence problem I, detection of the interest points.
4. Correspondence problem II, computing local invariant description.
5. Correspondence problem III, finding tenative correspondences and RANSAC.
6. Correspondence problem, summary.
7. Convolutional Neural Networks: training a classifier.D LN recording 2022
8. Convolutional Neural Networks II: debugging training process.
9. Image Retrieval, BoW TF-IDF, fast spatial verification.
10. Assignment defence.
11. Deep metric learning.
12. Self-supervised Learning.
13. Tracking.

Literature:

D. A. Forsyth, J. Ponce. Computer Vision: A Modern Approach. Prentice Hall 2003
I. Goodfellow, Y. Bengio, A. Courville: Deep Learning, 2016
A. Torralba, P. Isola, W. T. Freeman: Foundations of Computer Vision,

Requirements:

Knowledge of calculus and linear algebra.

Note:

URL: https://cw.fel.cvut.cz/wiki/courses/mpv/start

Keywords:

image registration, segmentation, object detection, tracking

Subject is included into these academic programs:

Program Branch Role Recommended semester
MPPRGAI_2025 Common courses P 2
MEBIO2_2018 Medical Instrumentation PV 2
MEOI5_2018 Computer Vision and Image Processing PO 2
MEBIO3_2018 Image Processing PS 2
MEKYR_2021 Common courses PV 2
MEBIO1_2018 Bioinformatics PV 2
MEBIO4_2018 Signal Processing PV 2


Page updated 19.2.2026 07:51:22, semester: Z/2026-7, L/2025-6, Z,L/2027-8, L/2026-7, Send comments about the content to the Administrators of the Academic Programs Proposal and Realization: I. Halaška (K336), J. Novák (K336)