A case for using rotation invariant features in state of the art feature matchers
2022-04-21Code Available1· sign in to hype
Georg Bökman, Fredrik Kahl
Code Available — Be the first to reproduce this paper.
ReproduceCode
- github.com/georg-bn/se2-loftrOfficialIn paperpytorch★ 92
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.