MatchBench: An Evaluation of Feature Matchers

TL;DR

This paper introduces MatchBench, a comprehensive benchmark for evaluating feature matchers in computer vision, addressing the lack of standard datasets and metrics to fairly compare different matchers and guide future research.

Contribution

It presents the first uniform benchmark for feature matchers, evaluating their ability, efficiency, and performance across various scenes and matching types, with extensive analysis of state-of-the-art methods.

Findings

Matchers vary significantly in performance across different scenes.

The benchmark reveals strengths and weaknesses of current feature matchers.

Results guide practical system design and future research directions.

Abstract

Feature matching is one of the most fundamental and active research areas in computer vision. A comprehensive evaluation of feature matchers is necessary, since it would advance both the development of this field and also high-level applications such as Structure-from-Motion or Visual SLAM. However, to the best of our knowledge, no previous work targets the evaluation of feature matchers while they only focus on evaluating feature detectors and descriptors. This leads to a critical absence in this field that there is no standard datasets and evaluation metrics to evaluate different feature matchers fairly. To this end, we present the first uniform feature matching benchmark to facilitate the evaluation of feature matchers. In the proposed benchmark, matchers are evaluated in different aspects, involving matching ability, correspondence sufficiency, and efficiency. Also, their performances are investigated in different scenes and in different matching types. Subsequently, we carry out an extensive evaluation of different state-of-the-art matchers on the benchmark and make in-depth analyses based on the reported results. This can be used to design practical matching systems in real applications and also advocates the potential future research directions in the field of feature matching.