Skeleton-based multiview reconstruction

The advantage of skeleton-based 3D reconstruction is to completely generate a single 3D object from well chosen views. Having numerous views is necessary for a reliable reconstruction but projections of skeletons lead to different topologies. We reconstruct 3D objects with curved medial axis (whose...

Full description

Saved in:
Bibliographic Details
Main Authors: Durix, Bastien, Morin, Geraldine, Chambon, Sylvie, Roudet, Celine, Garnier, Lionel
Format: Conference Proceeding
Language:English
Subjects:
Extremities
graph-edit distance
Image reconstruction
Labeling
reconstruction
Shape
Skeleton
Three-dimensional displays
Topology
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
cited_by
cites
container_end_page 4051
container_issue
container_start_page 4047
container_title
container_volume
creator Durix, Bastien
Morin, Geraldine
Chambon, Sylvie
Roudet, Celine
Garnier, Lionel
description The advantage of skeleton-based 3D reconstruction is to completely generate a single 3D object from well chosen views. Having numerous views is necessary for a reliable reconstruction but projections of skeletons lead to different topologies. We reconstruct 3D objects with curved medial axis (whose topology is a tree) from the perspective skeletons on an arbitrary number of calibrated acquisitions. The main contribution is to estimate the 3D skeleton, from multiple images: its topology is chosen as the closest to those of the perspective skeletons on the set of images, which means that the number of topology changes to map the 3D skeleton topology to topologies on images is minimum. This way, the number of matched branches is maximum.
doi_str_mv 10.1109/ICIP.2016.7533120
format conference_proceeding
fullrecord <record><control><sourceid>ieee_CHZPO</sourceid><recordid>TN_cdi_ieee_primary_7533120</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>7533120</ieee_id><sourcerecordid>7533120</sourcerecordid><originalsourceid>FETCH-LOGICAL-i175t-929ca893a9fcba731b34144b8d5c397a3bf4441d9478f5e490a511af7f0daa0c3</originalsourceid><addsrcrecordid>eNotj8FKxDAUAKMguK77AeJlb55S8_qSJu8oRdfCgoJ6Xl7SBKLdVtqu4t8ruKe5DAMjxBWoAkDRbVM3z0WpoCqsQYRSnYgVWQe6skhUQXUqFiU6kM5oOhcX0_Su1J-PsBA3Lx-xi_PQS89TbNf7Qzfnrxy_12MMQz_N4yHMeegvxVniboqrI5fi7eH-tX6U26dNU99tZQZrZkklBXaETCl4tggeNWjtXWsCkmX0SWsNLWnrkomaFBsATjapllkFXIrr_26OMe4-x7zn8Wd3_MJfQ5xBEg</addsrcrecordid><sourcetype>Publisher</sourcetype><iscdi>true</iscdi><recordtype>conference_proceeding</recordtype></control><display><type>conference_proceeding</type><title>Skeleton-based multiview reconstruction</title><source>IEEE Xplore All Conference Series</source><creator>Durix, Bastien ; Morin, Geraldine ; Chambon, Sylvie ; Roudet, Celine ; Garnier, Lionel</creator><creatorcontrib>Durix, Bastien ; Morin, Geraldine ; Chambon, Sylvie ; Roudet, Celine ; Garnier, Lionel</creatorcontrib><description>The advantage of skeleton-based 3D reconstruction is to completely generate a single 3D object from well chosen views. Having numerous views is necessary for a reliable reconstruction but projections of skeletons lead to different topologies. We reconstruct 3D objects with curved medial axis (whose topology is a tree) from the perspective skeletons on an arbitrary number of calibrated acquisitions. The main contribution is to estimate the 3D skeleton, from multiple images: its topology is chosen as the closest to those of the perspective skeletons on the set of images, which means that the number of topology changes to map the 3D skeleton topology to topologies on images is minimum. This way, the number of matched branches is maximum.</description><identifier>EISSN: 2381-8549</identifier><identifier>EISBN: 9781467399616</identifier><identifier>EISBN: 1467399612</identifier><identifier>DOI: 10.1109/ICIP.2016.7533120</identifier><language>eng</language><publisher>IEEE</publisher><subject>Extremities ; graph-edit distance ; Image reconstruction ; Labeling ; reconstruction ; Shape ; Skeleton ; Three-dimensional displays ; Topology</subject><ispartof>2016 IEEE International Conference on Image Processing (ICIP), 2016, p.4047-4051</ispartof><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://ieeexplore.ieee.org/document/7533120$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>309,310,780,784,789,790,27925,54555,54932</link.rule.ids><linktorsrc>$$Uhttps://ieeexplore.ieee.org/document/7533120$$EView_record_in_IEEE$$FView_record_in_$$GIEEE</linktorsrc></links><search><creatorcontrib>Durix, Bastien</creatorcontrib><creatorcontrib>Morin, Geraldine</creatorcontrib><creatorcontrib>Chambon, Sylvie</creatorcontrib><creatorcontrib>Roudet, Celine</creatorcontrib><creatorcontrib>Garnier, Lionel</creatorcontrib><title>Skeleton-based multiview reconstruction</title><title>2016 IEEE International Conference on Image Processing (ICIP)</title><addtitle>ICIP</addtitle><description>The advantage of skeleton-based 3D reconstruction is to completely generate a single 3D object from well chosen views. Having numerous views is necessary for a reliable reconstruction but projections of skeletons lead to different topologies. We reconstruct 3D objects with curved medial axis (whose topology is a tree) from the perspective skeletons on an arbitrary number of calibrated acquisitions. The main contribution is to estimate the 3D skeleton, from multiple images: its topology is chosen as the closest to those of the perspective skeletons on the set of images, which means that the number of topology changes to map the 3D skeleton topology to topologies on images is minimum. This way, the number of matched branches is maximum.</description><subject>Extremities</subject><subject>graph-edit distance</subject><subject>Image reconstruction</subject><subject>Labeling</subject><subject>reconstruction</subject><subject>Shape</subject><subject>Skeleton</subject><subject>Three-dimensional displays</subject><subject>Topology</subject><issn>2381-8549</issn><isbn>9781467399616</isbn><isbn>1467399612</isbn><fulltext>true</fulltext><rsrctype>conference_proceeding</rsrctype><creationdate>2016</creationdate><recordtype>conference_proceeding</recordtype><sourceid>6IE</sourceid><recordid>eNotj8FKxDAUAKMguK77AeJlb55S8_qSJu8oRdfCgoJ6Xl7SBKLdVtqu4t8ruKe5DAMjxBWoAkDRbVM3z0WpoCqsQYRSnYgVWQe6skhUQXUqFiU6kM5oOhcX0_Su1J-PsBA3Lx-xi_PQS89TbNf7Qzfnrxy_12MMQz_N4yHMeegvxVniboqrI5fi7eH-tX6U26dNU99tZQZrZkklBXaETCl4tggeNWjtXWsCkmX0SWsNLWnrkomaFBsATjapllkFXIrr_26OMe4-x7zn8Wd3_MJfQ5xBEg</recordid><startdate>201609</startdate><enddate>201609</enddate><creator>Durix, Bastien</creator><creator>Morin, Geraldine</creator><creator>Chambon, Sylvie</creator><creator>Roudet, Celine</creator><creator>Garnier, Lionel</creator><general>IEEE</general><scope>6IE</scope><scope>6IH</scope><scope>CBEJK</scope><scope>RIE</scope><scope>RIO</scope></search><sort><creationdate>201609</creationdate><title>Skeleton-based multiview reconstruction</title><author>Durix, Bastien ; Morin, Geraldine ; Chambon, Sylvie ; Roudet, Celine ; Garnier, Lionel</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-i175t-929ca893a9fcba731b34144b8d5c397a3bf4441d9478f5e490a511af7f0daa0c3</frbrgroupid><rsrctype>conference_proceedings</rsrctype><prefilter>conference_proceedings</prefilter><language>eng</language><creationdate>2016</creationdate><topic>Extremities</topic><topic>graph-edit distance</topic><topic>Image reconstruction</topic><topic>Labeling</topic><topic>reconstruction</topic><topic>Shape</topic><topic>Skeleton</topic><topic>Three-dimensional displays</topic><topic>Topology</topic><toplevel>online_resources</toplevel><creatorcontrib>Durix, Bastien</creatorcontrib><creatorcontrib>Morin, Geraldine</creatorcontrib><creatorcontrib>Chambon, Sylvie</creatorcontrib><creatorcontrib>Roudet, Celine</creatorcontrib><creatorcontrib>Garnier, Lionel</creatorcontrib><collection>IEEE Electronic Library (IEL) Conference Proceedings</collection><collection>IEEE Proceedings Order Plan (POP) 1998-present by volume</collection><collection>IEEE Xplore All Conference Proceedings</collection><collection>IEEE/IET Electronic Library</collection><collection>IEEE Proceedings Order Plans (POP) 1998-present</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Durix, Bastien</au><au>Morin, Geraldine</au><au>Chambon, Sylvie</au><au>Roudet, Celine</au><au>Garnier, Lionel</au><format>book</format><genre>proceeding</genre><ristype>CONF</ristype><atitle>Skeleton-based multiview reconstruction</atitle><btitle>2016 IEEE International Conference on Image Processing (ICIP)</btitle><stitle>ICIP</stitle><date>2016-09</date><risdate>2016</risdate><spage>4047</spage><epage>4051</epage><pages>4047-4051</pages><eissn>2381-8549</eissn><eisbn>9781467399616</eisbn><eisbn>1467399612</eisbn><abstract>The advantage of skeleton-based 3D reconstruction is to completely generate a single 3D object from well chosen views. Having numerous views is necessary for a reliable reconstruction but projections of skeletons lead to different topologies. We reconstruct 3D objects with curved medial axis (whose topology is a tree) from the perspective skeletons on an arbitrary number of calibrated acquisitions. The main contribution is to estimate the 3D skeleton, from multiple images: its topology is chosen as the closest to those of the perspective skeletons on the set of images, which means that the number of topology changes to map the 3D skeleton topology to topologies on images is minimum. This way, the number of matched branches is maximum.</abstract><pub>IEEE</pub><doi>10.1109/ICIP.2016.7533120</doi><tpages>5</tpages></addata></record>
fulltext fulltext_linktorsrc
identifier EISSN: 2381-8549
ispartof 2016 IEEE International Conference on Image Processing (ICIP), 2016, p.4047-4051
issn 2381-8549
language eng
recordid cdi_ieee_primary_7533120
source IEEE Xplore All Conference Series
subjects Extremities
graph-edit distance
Image reconstruction
Labeling
reconstruction
Shape
Skeleton
Three-dimensional displays
Topology
title Skeleton-based multiview reconstruction
url http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-28T07%3A33%3A27IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-ieee_CHZPO&rft_val_fmt=info:ofi/fmt:kev:mtx:book&rft.genre=proceeding&rft.atitle=Skeleton-based%20multiview%20reconstruction&rft.btitle=2016%20IEEE%20International%20Conference%20on%20Image%20Processing%20(ICIP)&rft.au=Durix,%20Bastien&rft.date=2016-09&rft.spage=4047&rft.epage=4051&rft.pages=4047-4051&rft.eissn=2381-8549&rft_id=info:doi/10.1109/ICIP.2016.7533120&rft.eisbn=9781467399616&rft.eisbn_list=1467399612&rft_dat=%3Cieee_CHZPO%3E7533120%3C/ieee_CHZPO%3E%3Cgrp_id%3Ecdi_FETCH-LOGICAL-i175t-929ca893a9fcba731b34144b8d5c397a3bf4441d9478f5e490a511af7f0daa0c3%3C/grp_id%3E%3Coa%3E%3C/oa%3E%3Curl%3E%3C/url%3E&rft_id=info:oai/&rft_id=info:pmid/&rft_ieee_id=7533120&rfr_iscdi=true