Geometric Image Correspondence Verification By Dense Pixel Matching

Abstract

This paper addresses the problem of determining dense pixel correspondences between two images and its application to geometric correspondence verification in image retrieval. The main contribution is a geometric correspondence verification approach for re-ranking a shortlist of retrieved database images based on their dense pair-wise matching with the query image at a pixel level. We determine a set of cyclically consistent dense pixel matches between the pair of images and evaluate local similarity of matched pixels using neural network based image descriptors. Final re-ranking is based on a novel similarity function, which fuses the local similarity metric with a global similarity metric and a geometric consistency measure computed for the matched pixels. For dense matching our approach utilizes a modified version of a recently proposed dense geometric correspondence network (DGC-Net), which we also improve by optimizing the architecture. The proposed model and similarity metric com

Stats

• citations8
• S2 citations—
• github stars0
• HF likes0
• heat score7.16
• arxiv keylaskar2019geometric

Related papers

• Correlation Verification For Image Retrieval (2022)18.80
• Differential Geometric Retrieval Of Deep Features (2017)2.26
• Hierarchical Metric Learning And Matching For 2D And 3D Geometric Correspondences (2018)11.39
• Sparse-to-dense Hypercolumn Matching For Long-term Visual Localization (2019)12.99
• Multi-view Dense Image Matching With Similarity Learning And Geometry Priors (2025)0.00
• Leveraging Semantic Cues From Foundation Vision Models For Enhanced Local Feature Correspondence (2024)5.24
• Viewpoint Invariant Dense Matching For Visual Geolocalization (2021)15.04
• Cross-view Image Matching For Geo-localization In Urban Environments (2017)17.16