No Cover Image

Conference Paper/Proceeding/Abstract 1074 views 355 downloads

Robust and Flexible Puzzle Solving with Corner-based Cycle Consistent Correspondences

Taiwei Wang, Kristiyan Vladimirov, Shuyu Goh, Yukai Lai, Xianghua Xie, Gary Tam Orcid Logo

EG UK Conference of Computer Graphics & Visual Computing 2019

Swansea University Author: Gary Tam Orcid Logo

DOI (Published version): 10.2312/cgvc.20191266

Abstract

Solving jigsaw puzzles is a classic problem in computer vision with various applications. Over the past decades, many useful approaches have been introduced. Most existing works use edge-wise similarity measures for assembling puzzles with square pieces of the same size, and recent work innovates to...

Full description

Published in: EG UK Conference of Computer Graphics & Visual Computing 2019
Published: Bangor, UK EGUK 2019
Online Access: http://eguk.bangor.ac.uk/CGVC2019/programme.html
URI: https://cronfa.swan.ac.uk/Record/cronfa51628
Tags: Add Tag
No Tags, Be the first to tag this record!
first_indexed 2019-09-06T04:44:01Z
last_indexed 2023-04-15T03:03:08Z
id cronfa51628
recordtype SURis
fullrecord <?xml version="1.0"?><rfc1807><datestamp>2023-04-14T15:22:45.9601322</datestamp><bib-version>v2</bib-version><id>51628</id><entry>2019-08-29</entry><title>Robust and Flexible Puzzle Solving with Corner-based Cycle Consistent Correspondences</title><swanseaauthors><author><sid>e75a68e11a20e5f1da94ee6e28ff5e76</sid><ORCID>0000-0001-7387-5180</ORCID><firstname>Gary</firstname><surname>Tam</surname><name>Gary Tam</name><active>true</active><ethesisStudent>false</ethesisStudent></author></swanseaauthors><date>2019-08-29</date><deptcode>SCS</deptcode><abstract>Solving jigsaw puzzles is a classic problem in computer vision with various applications. Over the past decades, many useful approaches have been introduced. Most existing works use edge-wise similarity measures for assembling puzzles with square pieces of the same size, and recent work innovates to use the loop constraint to improve efficiency and accuracy. We observe that most existing techniques cannot be easily extended to puzzles with rectangular pieces of arbitrary sizes, and no existing loop constraints can be used to model such challenging scenarios. In this paper, we propose a new corner-wise matching approach, modelled using the MatchLift framework to solve square puzzles with cycle consistency. We further show one exciting example illustrating how puzzles with rectangular pieces of arbitrary sizes would be solved by our technique.</abstract><type>Conference Paper/Proceeding/Abstract</type><journal>EG UK Conference of Computer Graphics &amp; Visual Computing 2019</journal><volume/><journalNumber/><paginationStart/><paginationEnd/><publisher>EGUK</publisher><placeOfPublication>Bangor, UK</placeOfPublication><isbnPrint/><isbnElectronic/><issnPrint/><issnElectronic/><keywords/><publishedDay>12</publishedDay><publishedMonth>9</publishedMonth><publishedYear>2019</publishedYear><publishedDate>2019-09-12</publishedDate><doi>10.2312/cgvc.20191266</doi><url>http://eguk.bangor.ac.uk/CGVC2019/programme.html</url><notes/><college>COLLEGE NANME</college><department>Computer Science</department><CollegeCode>COLLEGE CODE</CollegeCode><DepartmentCode>SCS</DepartmentCode><institution>Swansea University</institution><apcterm/><funders/><projectreference/><lastEdited>2023-04-14T15:22:45.9601322</lastEdited><Created>2019-08-29T15:20:49.0650022</Created><path><level id="1">Faculty of Science and Engineering</level><level id="2">School of Mathematics and Computer Science - Computer Science</level></path><authors><author><firstname>Taiwei</firstname><surname>Wang</surname><order>1</order></author><author><firstname>Kristiyan</firstname><surname>Vladimirov</surname><order>2</order></author><author><firstname>Shuyu</firstname><surname>Goh</surname><order>3</order></author><author><firstname>Yukai</firstname><surname>Lai</surname><order>4</order></author><author><firstname>Xianghua</firstname><surname>Xie</surname><order>5</order></author><author><firstname>Gary</firstname><surname>Tam</surname><orcid>0000-0001-7387-5180</orcid><order>6</order></author></authors><documents><document><filename>0051628-29082019152141.pdf</filename><originalFilename>wang19cgvc.pdf</originalFilename><uploaded>2019-08-29T15:21:41.6800000</uploaded><type>Output</type><contentLength>22907390</contentLength><contentType>application/pdf</contentType><version>Accepted Manuscript</version><cronfaStatus>true</cronfaStatus><embargoDate>2020-02-29T00:00:00.0000000</embargoDate><copyrightCorrect>false</copyrightCorrect><language>eng</language></document></documents><OutputDurs/></rfc1807>
spelling 2023-04-14T15:22:45.9601322 v2 51628 2019-08-29 Robust and Flexible Puzzle Solving with Corner-based Cycle Consistent Correspondences e75a68e11a20e5f1da94ee6e28ff5e76 0000-0001-7387-5180 Gary Tam Gary Tam true false 2019-08-29 SCS Solving jigsaw puzzles is a classic problem in computer vision with various applications. Over the past decades, many useful approaches have been introduced. Most existing works use edge-wise similarity measures for assembling puzzles with square pieces of the same size, and recent work innovates to use the loop constraint to improve efficiency and accuracy. We observe that most existing techniques cannot be easily extended to puzzles with rectangular pieces of arbitrary sizes, and no existing loop constraints can be used to model such challenging scenarios. In this paper, we propose a new corner-wise matching approach, modelled using the MatchLift framework to solve square puzzles with cycle consistency. We further show one exciting example illustrating how puzzles with rectangular pieces of arbitrary sizes would be solved by our technique. Conference Paper/Proceeding/Abstract EG UK Conference of Computer Graphics & Visual Computing 2019 EGUK Bangor, UK 12 9 2019 2019-09-12 10.2312/cgvc.20191266 http://eguk.bangor.ac.uk/CGVC2019/programme.html COLLEGE NANME Computer Science COLLEGE CODE SCS Swansea University 2023-04-14T15:22:45.9601322 2019-08-29T15:20:49.0650022 Faculty of Science and Engineering School of Mathematics and Computer Science - Computer Science Taiwei Wang 1 Kristiyan Vladimirov 2 Shuyu Goh 3 Yukai Lai 4 Xianghua Xie 5 Gary Tam 0000-0001-7387-5180 6 0051628-29082019152141.pdf wang19cgvc.pdf 2019-08-29T15:21:41.6800000 Output 22907390 application/pdf Accepted Manuscript true 2020-02-29T00:00:00.0000000 false eng
title Robust and Flexible Puzzle Solving with Corner-based Cycle Consistent Correspondences
spellingShingle Robust and Flexible Puzzle Solving with Corner-based Cycle Consistent Correspondences
Gary Tam
title_short Robust and Flexible Puzzle Solving with Corner-based Cycle Consistent Correspondences
title_full Robust and Flexible Puzzle Solving with Corner-based Cycle Consistent Correspondences
title_fullStr Robust and Flexible Puzzle Solving with Corner-based Cycle Consistent Correspondences
title_full_unstemmed Robust and Flexible Puzzle Solving with Corner-based Cycle Consistent Correspondences
title_sort Robust and Flexible Puzzle Solving with Corner-based Cycle Consistent Correspondences
author_id_str_mv e75a68e11a20e5f1da94ee6e28ff5e76
author_id_fullname_str_mv e75a68e11a20e5f1da94ee6e28ff5e76_***_Gary Tam
author Gary Tam
author2 Taiwei Wang
Kristiyan Vladimirov
Shuyu Goh
Yukai Lai
Xianghua Xie
Gary Tam
format Conference Paper/Proceeding/Abstract
container_title EG UK Conference of Computer Graphics & Visual Computing 2019
publishDate 2019
institution Swansea University
doi_str_mv 10.2312/cgvc.20191266
publisher EGUK
college_str Faculty of Science and Engineering
hierarchytype
hierarchy_top_id facultyofscienceandengineering
hierarchy_top_title Faculty of Science and Engineering
hierarchy_parent_id facultyofscienceandengineering
hierarchy_parent_title Faculty of Science and Engineering
department_str School of Mathematics and Computer Science - Computer Science{{{_:::_}}}Faculty of Science and Engineering{{{_:::_}}}School of Mathematics and Computer Science - Computer Science
url http://eguk.bangor.ac.uk/CGVC2019/programme.html
document_store_str 1
active_str 0
description Solving jigsaw puzzles is a classic problem in computer vision with various applications. Over the past decades, many useful approaches have been introduced. Most existing works use edge-wise similarity measures for assembling puzzles with square pieces of the same size, and recent work innovates to use the loop constraint to improve efficiency and accuracy. We observe that most existing techniques cannot be easily extended to puzzles with rectangular pieces of arbitrary sizes, and no existing loop constraints can be used to model such challenging scenarios. In this paper, we propose a new corner-wise matching approach, modelled using the MatchLift framework to solve square puzzles with cycle consistency. We further show one exciting example illustrating how puzzles with rectangular pieces of arbitrary sizes would be solved by our technique.
published_date 2019-09-12T04:03:36Z
_version_ 1763753293172965376
score 11.036706

Similar Items