A Case for Using Rotation Invariant Features in State of the Art Feature Matchers

Georg Bökman, Fredrik Kahl; Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2022, pp. 5110-5119

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.

Related Material

[pdf]
[bibtex]
@InProceedings{Bokman_2022_CVPR, author = {B\"okman, Georg and Kahl, Fredrik}, title = {A Case for Using Rotation Invariant Features in State of the Art Feature Matchers}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2022}, pages = {5110-5119} }