Geometric Image Correspondence Verification by Dense Pixel Matching

Research output: Chapter in Book/Report/Conference proceedingConference contributionScientificpeer-review

1 Citation (Scopus)

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 compare favourably to the state-of-the-art image retrieval methods. In addition, we apply our method to the problem of longterm visual localization demonstrating promising results and generalization across datasets.

Original languageEnglish
Title of host publicationIEEE Winter Conference on Applications of Computer Vision
PublisherIEEE
Pages2510-2519
Number of pages10
ISBN (Electronic)978-1-7281-6553-0
DOIs
Publication statusPublished - Mar 2020
MoE publication typeA4 Article in a conference publication
EventIEEE Winter Conference on Applications of Computer Vision - Snowmass Village, United States
Duration: 1 Mar 20205 Mar 2020

Conference

ConferenceIEEE Winter Conference on Applications of Computer Vision
Abbreviated titleWACV
CountryUnited States
CitySnowmass Village
Period01/03/202005/03/2020

Fingerprint

Dive into the research topics of 'Geometric Image Correspondence Verification by Dense Pixel Matching'. Together they form a unique fingerprint.

Cite this