No Cover Image

Other 141 views

Consistent Segment-wise Matching with Multi-Layer Graphs (CGVC2018 Poster) / Xianghua, Xie

International Conference on Geometric Modeling and Processing

Swansea University Author: Xianghua, Xie

Abstract

Segment-wise matching is an important research problem that supports higher-level understanding ofshapes in geometry processing. Many existing segment-wise matching techniques assume perfect input seg-mentation, and would suffer from imperfect or over-segmented input. To handle this shortcoming, we...

Full description

Published in: International Conference on Geometric Modeling and Processing
Online Access: http://www.eguk.org.uk/CGVC2018/programme.html
URI: https://cronfa.swan.ac.uk/Record/cronfa49120
Tags: Add Tag
No Tags, Be the first to tag this record!
first_indexed 2019-03-05T20:00:05Z
last_indexed 2019-06-14T20:46:32Z
id cronfa49120
recordtype SURis
fullrecord <?xml version="1.0"?><rfc1807><datestamp>2019-06-13T16:42:58.9586159</datestamp><bib-version>v2</bib-version><id>49120</id><entry>2019-03-05</entry><title>Consistent Segment-wise Matching with Multi-Layer Graphs (CGVC2018 Poster)</title><swanseaauthors><author><sid>b334d40963c7a2f435f06d2c26c74e11</sid><ORCID>0000-0002-2701-8660</ORCID><firstname>Xianghua</firstname><surname>Xie</surname><name>Xianghua Xie</name><active>true</active><ethesisStudent>false</ethesisStudent></author></swanseaauthors><date>2019-03-05</date><deptcode>SCS</deptcode><abstract>Segment-wise matching is an important research problem that supports higher-level understanding ofshapes in geometry processing. Many existing segment-wise matching techniques assume perfect input seg-mentation, and would suffer from imperfect or over-segmented input. To handle this shortcoming, we proposemulti-layer graphs (MLGs) to represent possible arrangements of partially merged segments of input shapes.We then adapt the diffusion pruning technique on the MLGs to find consistent segment-wise matching. Toobtain high quality matching, we develop a voting step to find hierarchically consistent correspondences asfinal output. We evaluate our technique with both qualitative and quantitative experiments on both man-made and deformable shapes. Experimental results demonstrate the effectiveness of our technique whencompared to two state-of-the-art methods.</abstract><type>Other</type><journal>International Conference on Geometric Modeling and Processing</journal><publisher/><keywords/><publishedDay>0</publishedDay><publishedMonth>0</publishedMonth><publishedYear>0</publishedYear><publishedDate>0001-01-01</publishedDate><doi/><url>http://www.eguk.org.uk/CGVC2018/programme.html</url><notes/><college>COLLEGE NANME</college><department>Computer Science</department><CollegeCode>COLLEGE CODE</CollegeCode><DepartmentCode>SCS</DepartmentCode><institution>Swansea University</institution><lastEdited>2019-06-13T16:42:58.9586159</lastEdited><Created>2019-03-05T12:52:42.1824484</Created><path><level id="1">College of Science</level><level id="2">Computer Science</level></path><authors><author><firstname>Taiwei</firstname><surname>Wang</surname><order>1</order></author><author><firstname>David</firstname><surname>George</surname><order>2</order></author><author><firstname>Yu-kun</firstname><surname>Lai</surname><order>3</order></author><author><firstname>Xianghua</firstname><surname>Xie</surname><orcid>0000-0002-2701-8660</orcid><order>4</order></author><author><firstname>Gary</firstname><surname>Tam</surname><order>5</order></author></authors><documents/></rfc1807>
spelling 2019-06-13T16:42:58.9586159 v2 49120 2019-03-05 Consistent Segment-wise Matching with Multi-Layer Graphs (CGVC2018 Poster) b334d40963c7a2f435f06d2c26c74e11 0000-0002-2701-8660 Xianghua Xie Xianghua Xie true false 2019-03-05 SCS Segment-wise matching is an important research problem that supports higher-level understanding ofshapes in geometry processing. Many existing segment-wise matching techniques assume perfect input seg-mentation, and would suffer from imperfect or over-segmented input. To handle this shortcoming, we proposemulti-layer graphs (MLGs) to represent possible arrangements of partially merged segments of input shapes.We then adapt the diffusion pruning technique on the MLGs to find consistent segment-wise matching. Toobtain high quality matching, we develop a voting step to find hierarchically consistent correspondences asfinal output. We evaluate our technique with both qualitative and quantitative experiments on both man-made and deformable shapes. Experimental results demonstrate the effectiveness of our technique whencompared to two state-of-the-art methods. Other International Conference on Geometric Modeling and Processing 0 0 0 0001-01-01 http://www.eguk.org.uk/CGVC2018/programme.html COLLEGE NANME Computer Science COLLEGE CODE SCS Swansea University 2019-06-13T16:42:58.9586159 2019-03-05T12:52:42.1824484 College of Science Computer Science Taiwei Wang 1 David George 2 Yu-kun Lai 3 Xianghua Xie 0000-0002-2701-8660 4 Gary Tam 5
title Consistent Segment-wise Matching with Multi-Layer Graphs (CGVC2018 Poster)
spellingShingle Consistent Segment-wise Matching with Multi-Layer Graphs (CGVC2018 Poster)
Xianghua, Xie
title_short Consistent Segment-wise Matching with Multi-Layer Graphs (CGVC2018 Poster)
title_full Consistent Segment-wise Matching with Multi-Layer Graphs (CGVC2018 Poster)
title_fullStr Consistent Segment-wise Matching with Multi-Layer Graphs (CGVC2018 Poster)
title_full_unstemmed Consistent Segment-wise Matching with Multi-Layer Graphs (CGVC2018 Poster)
title_sort Consistent Segment-wise Matching with Multi-Layer Graphs (CGVC2018 Poster)
author_id_str_mv b334d40963c7a2f435f06d2c26c74e11
author_id_fullname_str_mv b334d40963c7a2f435f06d2c26c74e11_***_Xianghua, Xie
author Xianghua, Xie
format Other
container_title International Conference on Geometric Modeling and Processing
institution Swansea University
college_str College of Science
hierarchytype
hierarchy_top_id collegeofscience
hierarchy_top_title College of Science
hierarchy_parent_id collegeofscience
hierarchy_parent_title College of Science
department_str Computer Science{{{_:::_}}}College of Science{{{_:::_}}}Computer Science
url http://www.eguk.org.uk/CGVC2018/programme.html
document_store_str 0
active_str 0
description Segment-wise matching is an important research problem that supports higher-level understanding ofshapes in geometry processing. Many existing segment-wise matching techniques assume perfect input seg-mentation, and would suffer from imperfect or over-segmented input. To handle this shortcoming, we proposemulti-layer graphs (MLGs) to represent possible arrangements of partially merged segments of input shapes.We then adapt the diffusion pruning technique on the MLGs to find consistent segment-wise matching. Toobtain high quality matching, we develop a voting step to find hierarchically consistent correspondences asfinal output. We evaluate our technique with both qualitative and quantitative experiments on both man-made and deformable shapes. Experimental results demonstrate the effectiveness of our technique whencompared to two state-of-the-art methods.
published_date 0001-01-01T04:44:08Z
_version_ 1659301315968237568
score 10.884025