GS-Matching: Reconsidering Feature Matching task in Point Cloud Registration

TL;DR

This paper introduces GS-matching, a stable matching policy inspired by Gale-Shapley, which improves feature matching in point cloud registration by reducing false matches and enhancing registration accuracy, especially in low-overlap scenarios.

Contribution

The paper proposes a novel stable matching policy for point cloud registration that outperforms existing methods in efficiency and accuracy, supported by probabilistic analysis and extensive experiments.

Findings

GS-matching finds more non-repetitive inliers.

It achieves higher registration recall on multiple datasets.

The method is efficient under low-overlap conditions.

Abstract

Traditional point cloud registration (PCR) methods for feature matching often employ the nearest neighbor policy. This leads to many-to-one matches and numerous potential inliers without any corresponding point. Recently, some approaches have framed the feature matching task as an assignment problem to achieve optimal one-to-one matches. We argue that the transition to the Assignment problem is not reliable for general correspondence-based PCR. In this paper, we propose a heuristics stable matching policy called GS-matching, inspired by the Gale-Shapley algorithm. Compared to the other matching policies, our method can perform efficiently and find more non-repetitive inliers under low overlapping conditions. Furthermore, we employ the probability theory to analyze the feature matching task, providing new insights into this research problem. Extensive experiments validate the effectiveness of our matching policy, achieving better registration recall on multiple datasets.