A case for using rotation invariant features in state of the art feature matchers
Paper in proceeding, 2022
The aim of this paper is to demonstrate that a state of the art feature matcher (LoFTR) can be made more robust to rotations by simply replacing the backbone CNN with a steerable CNN which is equivariant to translations and image rotations. It is experimentally shown that this boost is obtained without reducing performance on ordinary illumination and viewpoint matching sequences.
Author
Georg Bökman
Chalmers, Electrical Engineering, Signal Processing and Biomedical Engineering
Fredrik Kahl
Chalmers, Electrical Engineering, Signal Processing and Biomedical Engineering
IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops
21607508 (ISSN) 21607516 (eISSN)
Vol. 2022-June 5106-51159781665487399 (ISBN)
2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2022
New Orleans, USA,
New Orleans, USA,
Subject Categories
Bioinformatics (Computational Biology)
Signal Processing
Computer Vision and Robotics (Autonomous Systems)
DOI
10.1109/CVPRW56347.2022.00559