A case for using rotation invariant features in state of the art feature matchers

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 with...

Full description

Saved in:
Bibliographic Details
Published in:arXiv.org 2022-07
Main Authors: Bökman, Georg, Kahl, Fredrik
Format: Article
Language:English
Subjects:
Translations
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary: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.
ISSN:2331-8422