No Cover Image

Conference Paper/Proceeding/Abstract 875 views 97 downloads

Shape Correspondence with Isometric and Non-Isometric Deformations

R. M. Dyke, C Stride, Y.-K. Lai, P. L. Rosin, M. Aubry, A. Boyarski, A. M. Bronstein, M. M. Bronstein, D. Cremers, M. Fisher, T. Groueix, D. Guo, V. G. Kim, R. Kimmel, Z. Lähner, K. Li, O. Litany, T. Remez, E. Rodolà, B. C. Russell, Y. Sahillioglu, R. Slossberg, M. Vestner, Z. Wu, J. Yang, Gary Tam Orcid Logo

Eurographics Workshop on 3D Object Retrieval

Swansea University Author: Gary Tam Orcid Logo

Check full text

DOI (Published version): 10.2312/3dor.20191069

Abstract

The registration of surfaces with non-rigid deformation, especially non-isometric deformations, is a challenging problem. When applying such techniques to real scans, the problem is compounded by topological and geometric inconsistencies between shapes. In this paper, we capture a benchmark dataset...

Full description

Published in: Eurographics Workshop on 3D Object Retrieval
ISBN: 978-3-03868-077-2
ISSN: 1997-0471
Published: The Eurographics Association 2019
Online Access: Check full text

URI: https://cronfa.swan.ac.uk/Record/cronfa52380
Tags: Add Tag
No Tags, Be the first to tag this record!
first_indexed 2019-10-08T14:22:37Z
last_indexed 2023-04-15T03:04:15Z
id cronfa52380
recordtype SURis
fullrecord <?xml version="1.0"?><rfc1807><datestamp>2023-04-14T15:27:58.9024688</datestamp><bib-version>v2</bib-version><id>52380</id><entry>2019-10-08</entry><title>Shape Correspondence with Isometric and Non-Isometric Deformations</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>2019-10-08</date><deptcode>SCS</deptcode><abstract>The registration of surfaces with non-rigid deformation, especially non-isometric deformations, is a challenging problem. When applying such techniques to real scans, the problem is compounded by topological and geometric inconsistencies between shapes. In this paper, we capture a benchmark dataset of scanned 3D shapes undergoing various controlled deformations (articulating, bending, stretching and topologically changing), along with ground truth correspondences. With the aid of thistiered benchmark of increasingly challenging real scans, we explore this problem and investigate how robust current stateof-the-art methods perform in different challenging registration andc orrespondence scenarios. We discover that changes in topology is a challenging problem for some methods and that machine learning-based approaches prove to be more capable of handling non-isometric deformations on shapes that are moderately similar to the training set.</abstract><type>Conference Paper/Proceeding/Abstract</type><journal>Eurographics Workshop on 3D Object Retrieval</journal><volume/><journalNumber/><paginationStart/><paginationEnd/><publisher>The Eurographics Association</publisher><placeOfPublication/><isbnPrint/><isbnElectronic>978-3-03868-077-2</isbnElectronic><issnPrint/><issnElectronic>1997-0471</issnElectronic><keywords/><publishedDay>29</publishedDay><publishedMonth>4</publishedMonth><publishedYear>2019</publishedYear><publishedDate>2019-04-29</publishedDate><doi>10.2312/3dor.20191069</doi><url>https://diglib.eg.org/handle/10.2312/3dor20191069</url><notes/><college>COLLEGE NANME</college><department>Computer Science</department><CollegeCode>COLLEGE CODE</CollegeCode><DepartmentCode>SCS</DepartmentCode><institution>Swansea University</institution><apcterm/><funders>This work has been supported by the Cardiff University EPSRC Doctoral Training Partnership [grant ref. EP/N509449/1], and by the Scientific and Technological Research Council of Turkey (T&#xDC;B&#x2D9;ITAK) [grant ref. EEEAG-115E471].</funders><projectreference/><lastEdited>2023-04-14T15:27:58.9024688</lastEdited><Created>2019-10-08T12:01:09.1164537</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>R. M.</firstname><surname>Dyke</surname><order>1</order></author><author><firstname>C</firstname><surname>Stride</surname><order>2</order></author><author><firstname>Y.-K.</firstname><surname>Lai</surname><order>3</order></author><author><firstname>P. L.</firstname><surname>Rosin</surname><order>4</order></author><author><firstname>M.</firstname><surname>Aubry</surname><order>5</order></author><author><firstname>A.</firstname><surname>Boyarski</surname><order>6</order></author><author><firstname>A. M.</firstname><surname>Bronstein</surname><order>7</order></author><author><firstname>M. M.</firstname><surname>Bronstein</surname><order>8</order></author><author><firstname>D.</firstname><surname>Cremers</surname><order>9</order></author><author><firstname>M.</firstname><surname>Fisher</surname><order>10</order></author><author><firstname>T.</firstname><surname>Groueix</surname><order>11</order></author><author><firstname>D.</firstname><surname>Guo</surname><order>12</order></author><author><firstname>V. G.</firstname><surname>Kim</surname><order>13</order></author><author><firstname>R.</firstname><surname>Kimmel</surname><order>14</order></author><author><firstname>Z.</firstname><surname>L&#xE4;hner</surname><order>15</order></author><author><firstname>K.</firstname><surname>Li</surname><order>16</order></author><author><firstname>O.</firstname><surname>Litany</surname><order>17</order></author><author><firstname>T.</firstname><surname>Remez</surname><order>18</order></author><author><firstname>E.</firstname><surname>Rodol&#xE0;</surname><order>19</order></author><author><firstname>B. C.</firstname><surname>Russell</surname><order>20</order></author><author><firstname>Y.</firstname><surname>Sahillioglu</surname><order>21</order></author><author><firstname>R.</firstname><surname>Slossberg</surname><order>22</order></author><author><firstname>M.</firstname><surname>Vestner</surname><order>23</order></author><author><firstname>Z.</firstname><surname>Wu</surname><order>24</order></author><author><firstname>J.</firstname><surname>Yang</surname><order>25</order></author><author><firstname>Gary</firstname><surname>Tam</surname><orcid>0000-0001-7387-5180</orcid><order>26</order></author></authors><documents><document><filename>52380__16280__2114b2a432d642c6bf020ca6d6c46f49.pdf</filename><originalFilename>52380.pdf</originalFilename><uploaded>2020-01-13T15:51:34.2495016</uploaded><type>Output</type><contentLength>2614122</contentLength><contentType>application/pdf</contentType><version>Version of Record</version><cronfaStatus>true</cronfaStatus><copyrightCorrect>true</copyrightCorrect><language>eng</language><licence>https://www.eg.org/wp/eurographics-publications/guidelines/#licensing</licence></document></documents><OutputDurs/></rfc1807>
spelling 2023-04-14T15:27:58.9024688 v2 52380 2019-10-08 Shape Correspondence with Isometric and Non-Isometric Deformations e75a68e11a20e5f1da94ee6e28ff5e76 0000-0001-7387-5180 Gary Tam Gary Tam true false 2019-10-08 SCS The registration of surfaces with non-rigid deformation, especially non-isometric deformations, is a challenging problem. When applying such techniques to real scans, the problem is compounded by topological and geometric inconsistencies between shapes. In this paper, we capture a benchmark dataset of scanned 3D shapes undergoing various controlled deformations (articulating, bending, stretching and topologically changing), along with ground truth correspondences. With the aid of thistiered benchmark of increasingly challenging real scans, we explore this problem and investigate how robust current stateof-the-art methods perform in different challenging registration andc orrespondence scenarios. We discover that changes in topology is a challenging problem for some methods and that machine learning-based approaches prove to be more capable of handling non-isometric deformations on shapes that are moderately similar to the training set. Conference Paper/Proceeding/Abstract Eurographics Workshop on 3D Object Retrieval The Eurographics Association 978-3-03868-077-2 1997-0471 29 4 2019 2019-04-29 10.2312/3dor.20191069 https://diglib.eg.org/handle/10.2312/3dor20191069 COLLEGE NANME Computer Science COLLEGE CODE SCS Swansea University This work has been supported by the Cardiff University EPSRC Doctoral Training Partnership [grant ref. EP/N509449/1], and by the Scientific and Technological Research Council of Turkey (TÜB˙ITAK) [grant ref. EEEAG-115E471]. 2023-04-14T15:27:58.9024688 2019-10-08T12:01:09.1164537 Faculty of Science and Engineering School of Mathematics and Computer Science - Computer Science R. M. Dyke 1 C Stride 2 Y.-K. Lai 3 P. L. Rosin 4 M. Aubry 5 A. Boyarski 6 A. M. Bronstein 7 M. M. Bronstein 8 D. Cremers 9 M. Fisher 10 T. Groueix 11 D. Guo 12 V. G. Kim 13 R. Kimmel 14 Z. Lähner 15 K. Li 16 O. Litany 17 T. Remez 18 E. Rodolà 19 B. C. Russell 20 Y. Sahillioglu 21 R. Slossberg 22 M. Vestner 23 Z. Wu 24 J. Yang 25 Gary Tam 0000-0001-7387-5180 26 52380__16280__2114b2a432d642c6bf020ca6d6c46f49.pdf 52380.pdf 2020-01-13T15:51:34.2495016 Output 2614122 application/pdf Version of Record true true eng https://www.eg.org/wp/eurographics-publications/guidelines/#licensing
title Shape Correspondence with Isometric and Non-Isometric Deformations
spellingShingle Shape Correspondence with Isometric and Non-Isometric Deformations
Gary Tam
title_short Shape Correspondence with Isometric and Non-Isometric Deformations
title_full Shape Correspondence with Isometric and Non-Isometric Deformations
title_fullStr Shape Correspondence with Isometric and Non-Isometric Deformations
title_full_unstemmed Shape Correspondence with Isometric and Non-Isometric Deformations
title_sort Shape Correspondence with Isometric and Non-Isometric Deformations
author_id_str_mv e75a68e11a20e5f1da94ee6e28ff5e76
author_id_fullname_str_mv e75a68e11a20e5f1da94ee6e28ff5e76_***_Gary Tam
author Gary Tam
author2 R. M. Dyke
C Stride
Y.-K. Lai
P. L. Rosin
M. Aubry
A. Boyarski
A. M. Bronstein
M. M. Bronstein
D. Cremers
M. Fisher
T. Groueix
D. Guo
V. G. Kim
R. Kimmel
Z. Lähner
K. Li
O. Litany
T. Remez
E. Rodolà
B. C. Russell
Y. Sahillioglu
R. Slossberg
M. Vestner
Z. Wu
J. Yang
Gary Tam
format Conference Paper/Proceeding/Abstract
container_title Eurographics Workshop on 3D Object Retrieval
publishDate 2019
institution Swansea University
isbn 978-3-03868-077-2
issn 1997-0471
doi_str_mv 10.2312/3dor.20191069
publisher The Eurographics Association
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 https://diglib.eg.org/handle/10.2312/3dor20191069
document_store_str 1
active_str 0
description The registration of surfaces with non-rigid deformation, especially non-isometric deformations, is a challenging problem. When applying such techniques to real scans, the problem is compounded by topological and geometric inconsistencies between shapes. In this paper, we capture a benchmark dataset of scanned 3D shapes undergoing various controlled deformations (articulating, bending, stretching and topologically changing), along with ground truth correspondences. With the aid of thistiered benchmark of increasingly challenging real scans, we explore this problem and investigate how robust current stateof-the-art methods perform in different challenging registration andc orrespondence scenarios. We discover that changes in topology is a challenging problem for some methods and that machine learning-based approaches prove to be more capable of handling non-isometric deformations on shapes that are moderately similar to the training set.
published_date 2019-04-29T04:04:42Z
_version_ 1763753363028049920
score 10.993443