An Evaluation of Feature Matchers for Fundamental Matrix Estimation

TL;DR

This paper evaluates recent feature matching algorithms for fundamental matrix estimation, comparing their performance within classical pipelines across large datasets, and proposes improved matching systems and a robust estimator for better practical applications.

Contribution

It provides a comprehensive evaluation of new feature matchers in fundamental matrix estimation and introduces three high-quality matching systems and a Coarse-to-Fine RANSAC estimator.

Findings

New algorithms outperform traditional methods on benchmark datasets.

Proposed systems show significant improvements in accuracy and robustness.

The evaluation pipeline and methods are publicly available for future research.

Abstract

Matching two images while estimating their relative geometry is a key step in many computer vision applications. For decades, a well-established pipeline, consisting of SIFT, RANSAC, and 8-point algorithm, has been used for this task. Recently, many new approaches were proposed and shown to outperform previous alternatives on standard benchmarks, including the learned features, correspondence pruning algorithms, and robust estimators. However, whether it is beneficial to incorporate them into the classic pipeline is less-investigated. To this end, we are interested in i) evaluating the performance of these recent algorithms in the context of image matching and epipolar geometry estimation, and ii) leveraging them to design more practical registration systems. The experiments are conducted in four large-scale datasets using strictly defined evaluation metrics, and the promising results provide insight into which algorithms suit which scenarios. According to this, we propose three high-quality matching systems and a Coarse-to-Fine RANSAC estimator. They show remarkable performances and have potentials to a large part of computer vision tasks. To facilitate future research, the full evaluation pipeline and the proposed methods are made publicly available.