A case for using rotation invariant features in state of the art feature matchers
This addresses robustness issues in computer vision tasks like image matching, but it is incremental as it modifies an existing method.
The paper tackled the problem of improving robustness to rotations in state-of-the-art feature matchers by replacing the backbone CNN with a steerable CNN, resulting in enhanced performance without reducing effectiveness on standard sequences.
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.