Boosting local matches with convolutional co-segmentation

Erez Farhan

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

Abstract

Matching corresponding local patches between images is a fundamental building block in many computer-vision algorithms. Most matching methods are composed of two main stages: feature extraction, typically done independently on each image, and feature matching which is done on processed representations. This strategy tends to create large amounts of matches, typically describing small, highly-textured regions within each image. In many cases, large portions of the corresponding images have a simple geometric relationship. We exploit this fact and reformulate the matching procedure to an estimation stage, where we extract large domains roughly related by local transformations, and a convolutional Co-Segmentation stage, for densely detecting accurate matches in every domain. Consequently, we represent the geometrical relationship between images with a concise list of accurately co-segmented domains, preserving the geometrical flexibility stemmed from local analysis. We show how the proposed co-segmentation improves the matching coverage to accurately include many low-textured domains.

Original languageEnglish
Title of host publicationProceedings - 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2019
PublisherInstitute of Electrical and Electronics Engineers
Pages8-15
Number of pages8
ISBN (Electronic)9781728125060
StatePublished - 1 Jun 2019
Event32nd IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2019 - Long Beach, United States
Duration: 16 Jun 201920 Jun 2019

Publication series

NameIEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops
Volume2019-June
ISSN (Print)2160-7508
ISSN (Electronic)2160-7516

Conference

Conference32nd IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2019
Country/TerritoryUnited States
CityLong Beach
Period16/06/1920/06/19

ASJC Scopus subject areas

  • Computer Vision and Pattern Recognition
  • Electrical and Electronic Engineering

Fingerprint

Dive into the research topics of 'Boosting local matches with convolutional co-segmentation'. Together they form a unique fingerprint.

Cite this