A case for using rotation invariant features in state of the art feature matchers
Abstract
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.
- Publication:
-
arXiv e-prints
- Pub Date:
- April 2022
- DOI:
- 10.48550/arXiv.2204.10144
- arXiv:
- arXiv:2204.10144
- Bibcode:
- 2022arXiv220410144B
- Keywords:
-
- Computer Science - Computer Vision and Pattern Recognition
- E-Print:
- CVPRW 2022, updated version