Locality-Guided Global-Preserving Optimization for Robust Feature Matching

Yifan Xia

doi:10.1109/TIP.2022.3192993

2022-01-01

PRE

Yifan Xia

马佳义 (Jiayi Ma) *

DOI：10.1109/TIP.2022.3192993

原文链接

原文求助

摘要

En 中文

Feature matching is a fundamental problem in many computer vision tasks. This paper proposes a novel effective framework for mismatch removal, named LOcality-guided Global-preserving Optimization (LOGO). To identify inliers from a putative matching set generated by feature descriptor similarity, we introduce a fixed-point progressive approach to optimize a graph-based objective, which represents a two-class assignment problem regarding an affinity matrix containing global structures. We introduce a strategy that a small initial set with a high inlier ratio exploits the topology of the affinity matrix to elicit other inliers based on their reliable geometry, which enhances the robustness to outliers. Geometrically, we provide a locality-guided matching strategy, i.e., using local topology consensus as a criterion to determine the initial set, thus expanding to yield the final feature matching set. In addition, we apply local affine transformations based on reference points to determine the local consensus and similarity scores of nodes and edges, ensuring the validity and generality for various scenarios including complex nonrigid transformations. Extensive experiments demonstrate the effectiveness and robustness of the proposed LOGO, which is competitive with the current state-of-the-art methods. It also exhibits favorable potential for high-level vision tasks, such as essential and fundamental matrix estimation, image registration and loop closure detection.

Keyword:

Topology

Optimization

Robustness

Task analysis

Feature extraction

Estimation

Strain

Feature matching

mismatch removal

locality-guided

graph optimization