See More, Match Better: Multi-Source Feature Fusion for Two-View Correspondence Learning

2026-06-08

AI Summary

This work addresses the challenge that existing methods struggle to disambiguate geometrically consistent yet semantically incorrect false inliers in scenes with repetitive structures, textureless regions, or locally similar geometry. To overcome this limitation, the authors propose TriMatch, a novel framework that integrates geometric, textural semantic, and structural semantic features. TriMatch introduces texture–geometry and structure–geometry alignment modules, a semantics-guided correspondence modulation mechanism, and a hierarchical semantic-aware refinement strategy, thereby transcending the constraints of conventional approaches that rely solely on geometric consistency. Experimental results demonstrate that TriMatch significantly outperforms state-of-the-art methods in terms of accuracy, robustness, and generalization capability.

Abstract

Two-view correspondence learning aims to distinguish true correspondences (inliers) from false ones (outliers) in image pairs by leveraging their underlying differences. Existing methods mainly rely on coordinate-based geometric consistency. However, they often struggle with pseudo-consistent outliers in scenes containing repetitive structures, textureless regions, or locally similar geometric patterns. To address this limitation, we propose TriMatch, a multi-source feature fusion framework for two-view correspondence learning, which consists of two parts: feature extraction and feature refinement. In feature extraction, TriMatch jointly extracts geometric, texture semantic, and structural semantic features to provide complementary evidence for correspondence discrimination. To bridge the gap between semantic and geometric features, texture and structural semantic features are aligned with geometric features through dedicated Texture-Geometric Alignment and Structural-Geometric Alignment modules, respectively. We further introduce a Semantic-Guided Correspondence Modulation module, which modulates geometric features using semantic information to suppress geometrically plausible but semantically inconsistent correspondences. In feature refinement, a Hierarchical Semantic-Enhanced Correspondence Refinement strategy progressively models correspondence dependencies and recalibrates multi-context feature responses, enabling more reliable inlier-outlier discrimination. Extensive experiments demonstrate the effectiveness, robustness, and generalization capability of TriMatch.

Problem

• two-view correspondence
• outlier rejection
• geometric consistency
• semantic features
• feature fusion

Innovation

• multi-source feature fusion
• semantic-geometric alignment
• correspondence modulation
• hierarchical refinement
• two-view correspondence learning