GlueStick: Robust Image Matching by Sticking Points and Lines Together

TL;DR

GlueStick introduces a unified wireframe-based deep GNN approach for robust image matching that leverages points and lines, significantly improving performance across various datasets and tasks.

Contribution

The paper presents a novel deep GNN framework that unifies point and line segment matching into a single wireframe structure, enhancing efficiency and accuracy.

Findings

Outperforms state-of-the-art methods in point and line matching

Leverages connectivity information for better matching accuracy

Demonstrates robustness across diverse datasets and conditions

Abstract

Line segments are powerful features complementary to points. They offer structural cues, robust to drastic viewpoint and illumination changes, and can be present even in texture-less areas. However, describing and matching them is more challenging compared to points due to partial occlusions, lack of texture, or repetitiveness. This paper introduces a new matching paradigm, where points, lines, and their descriptors are unified into a single wireframe structure. We propose GlueStick, a deep matching Graph Neural Network (GNN) that takes two wireframes from different images and leverages the connectivity information between nodes to better glue them together. In addition to the increased efficiency brought by the joint matching, we also demonstrate a large boost of performance when leveraging the complementary nature of these two features in a single architecture. We show that our matching strategy outperforms the state-of-the-art approaches independently matching line segments and points for a wide variety of datasets and tasks. The code is available at https://github.com/cvg/GlueStick.