SIM2E: Benchmarking the Group Equivariant Capability of Correspondence Matching Algorithms

TL;DR

This paper introduces SIM2E, a specialized dataset for benchmarking the ability of correspondence matching algorithms to handle similarity transformations, emphasizing the importance of group equivariant methods in computer vision.

Contribution

The paper presents a new dataset for evaluating sim(2)-equivariant correspondence matching algorithms and compares 16 state-of-the-art methods under various transformation conditions.

Findings

Group equivariant algorithms outperform non-equivariant ones.

Current CNN-based methods have limited subpixel accuracy.

The dataset highlights the need for improved equivariant matching techniques.

Abstract

Correspondence matching is a fundamental problem in computer vision and robotics applications. Solving correspondence matching problems using neural networks has been on the rise recently. Rotation-equivariance and scale-equivariance are both critical in correspondence matching applications. Classical correspondence matching approaches are designed to withstand scaling and rotation transformations. However, the features extracted using convolutional neural networks (CNNs) are only translation-equivariant to a certain extent. Recently, researchers have strived to improve the rotation-equivariance of CNNs based on group theories. Sim(2) is the group of similarity transformations in the 2D plane. This paper presents a specialized dataset dedicated to evaluating sim(2)-equivariant correspondence matching algorithms. We compare the performance of 16 state-of-the-art (SoTA) correspondence matching approaches. The experimental results demonstrate the importance of group equivariant algorithms for correspondence matching on various sim(2) transformation conditions. Since the subpixel accuracy achieved by CNN-based correspondence matching approaches is unsatisfactory, this specific area requires more attention in future works. Our dataset is publicly available at: mias.group/SIM2E.