MatchBench: An Evaluation of Feature Matchers
This addresses a critical gap for researchers and practitioners in computer vision by providing a standardized evaluation framework, though it is incremental as it builds on existing work on feature detectors and descriptors.
The paper tackles the lack of standardized evaluation for feature matchers in computer vision by introducing MatchBench, the first uniform benchmark to assess matchers across aspects like matching ability, correspondence sufficiency, and efficiency, with extensive analyses of state-of-the-art methods.
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.