False correspondence removal via revisiting semantic context with position-attentive learning

False correspondence removal remains a challenge for many feature-matching-based applications. This paper proposes a solution that revisits the local semantic context via position-attentive learning. First, a cross-divisional module is introduced to extract semantic features from image-patch pairs. Then, through a position-attentive mechanism, the parametric positions and extracted semantic features are jointly utilized to compute the probabilities of a set of putative correspondences. The proposed approach is evaluated on several indoor and outdoor challenging datasets, containing up to 70%+ false correspondences. In most cases, the solution outperforms existing algorithms in terms of matching precision and F1-score. Furthermore, an ablation study indicates that revisiting the semantic context improves precision by nearly 5%. The code is available at the link below (1).