SIM2E: Benchmarking the Group Equivariant Capability of Correspondence Matching Algorithms

08/21/2022
by   Shuai Su, et al.
0

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.

READ FULL TEXT

page 2

page 5

page 13

research
06/12/2023

Scale-Rotation-Equivariant Lie Group Convolution Neural Networks (Lie Group-CNNs)

The weight-sharing mechanism of convolutional kernels ensures translatio...
research
08/31/2023

E3CM: Epipolar-Constrained Cascade Correspondence Matching

Accurate and robust correspondence matching is of utmost importance for ...
research
03/10/2022

ReF – Rotation Equivariant Features for Local Feature Matching

Sparse local feature matching is pivotal for many computer vision and ro...
research
11/30/2021

cliquematch: Finding correspondence via cliques in large graphs

The maximum clique problem finds applications in computer vision, bioinf...
research
10/02/2020

Homography Estimation with Convolutional Neural Networks Under Conditions of Variance

Planar homography estimation is foundational to many computer vision pro...
research
01/03/2013

Investigating the performance of Correspondence Algorithms in Vision based Driver-assistance in Indoor Environment

This paper presents the experimental comparison of fourteen stereo match...
research
08/26/2019

An Evaluation of Feature Matchers forFundamental Matrix Estimation

Matching two images while estimating their relative geometry is a key st...

Please sign up or login with your details

Forgot password? Click here to reset