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

Georg Bökman, Fredrik Kahl

2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · 2022 · 44 citations · 37 references

Concepts

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.

References

37