Skip to the content.

The main objective of this tutorial is to present the theory and applications of affine correspondences (AC) in computer vision. The tutorial will show recent advancements in exploiting affine features in single- and two-view problems, including image rectification, homography and epipolar geometry estimation. Also, we will discuss traditional and recent deep learning-based algorithms for detecting, matching, and robustly using such features in real-world images.



Begin End Title
9.00 9.45 Introduction
9.45 11.15 Affine Correspondences in Stereo Vision
(SLIDE Levente Hajder)
11.15 12.45 Affine Correspondences and Where to Find Them
(SLIDE, Dmytro Mishkin)
12.45 14.00 Lunch Break
14.00 15.30 Just One Image is All It Takes: Rectification, Auto-Calibration and Scene Parsing from Affine-Correspondences of Coplanar Repetitive Textures
(SLIDE , VIDEO, James Pritts)
15.30 17.00 Using Covariant Features in Practice
(SLIDE, Daniel Barath)


Daniel Barath
Computer Vision and Geometry Group, ETH Zurich
Dmytro Mishkin
Center for Machine Perception, Department of Cybernetics, Faculty of Electrical Engineering, Czech Technical University, Prague
Levente Hajder
Geometric Computer Vision Group, Department of Algorithms and their Applications, Eötvös Loránd University
James Pritts
Applied Algebra & Geometry Group, Czech Institute of Informatics, Robotics and Cybernetics, Czech Technical University in Prague


Feb 15, 2022   Our tutorial has been accepted to CVPR 2022!
Apr 04, 2022   More information to come soon, stay tuned.