CVApr 21, 2022

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

arXiv:2204.10144v259 citationsh-index: 48
Originality Incremental advance
AI Analysis

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.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes