Template-based Monocular 3D Shape Recovery using Laplacian Meshes

Template-based Monocular 3D Shape Recovery using Laplacian Meshes

We show that by extending the Laplacian formalism, which was first introduced in the Graphics community to regularize 3D meshes, we can turn the monocular 3D shape reconstruction of a deformable surface given correspondences with a reference image into a much better-posed problem. This allows us to...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:arXiv.org 2015-05
Hauptverfasser: Dat Tien Ngo, Ostlund, Jonas, Fua, Pascal
Format: Artikel
Sprache:eng
Schlagworte:
Computer Science - Computer Vision and Pattern Recognition
Deformation
Formability
Image reconstruction
Least squares method
Optimization
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page
container_issue
container_start_page
container_title arXiv.org
container_volume
creator Dat Tien Ngo
Ostlund, Jonas
Fua, Pascal
description We show that by extending the Laplacian formalism, which was first introduced in the Graphics community to regularize 3D meshes, we can turn the monocular 3D shape reconstruction of a deformable surface given correspondences with a reference image into a much better-posed problem. This allows us to quickly and reliably eliminate outliers by simply solving a linear least squares problem. This yields an initial 3D shape estimate, which is not necessarily accurate, but whose 2D projections are. The initial shape is then refined by a constrained optimization problem to output the final surface reconstruction. Our approach allows us to reduce the dimensionality of the surface reconstruction problem without sacrificing accuracy, thus allowing for real-time implementations.
doi_str_mv 10.48550/arxiv.1503.04643
format Article
fullrecord <record><control><sourceid>proquest_arxiv</sourceid><recordid>TN_cdi_arxiv_primary_1503_04643</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2083393783</sourcerecordid><originalsourceid>FETCH-LOGICAL-a523-be4fa34e0066189decdf986e01c4ea1b4d96e2ef50a15b927b2a523a70759b83</originalsourceid><addsrcrecordid>eNotj0tvgkAUhSdNmtRYf0BXnaRr6J0XDEtjHzbBNKnuyQUuFYNAZ8TUf1_Ubu7ZfOfkfow9CAi1NQae0f3Wx1AYUCHoSKsbNpFKicBqKe_YzPsdAMgolsaoCZtvaN83eKAgR08lX3VtVwwNOq5e-HqLPfEvKrojuRMffN1-8xRHvqix5SvyW_L37LbCxtPsP6ds_fa6WSyD9PP9YzFPAzRSBTnpCpUmgCgSNimpKKvERgSi0IQi12USkaTKAAqTJzLO5bmHMcQmya2assfr6kUv6129R3fKzprZRXMknq5E77qfgfwh23WDa8eXMglWqUTF4_0DnGtUWA</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2083393783</pqid></control><display><type>article</type><title>Template-based Monocular 3D Shape Recovery using Laplacian Meshes</title><source>arXiv.org</source><source>Open Access: Freely Accessible Journals by multiple vendors</source><creator>Dat Tien Ngo ; Ostlund, Jonas ; Fua, Pascal</creator><creatorcontrib>Dat Tien Ngo ; Ostlund, Jonas ; Fua, Pascal</creatorcontrib><description>We show that by extending the Laplacian formalism, which was first introduced in the Graphics community to regularize 3D meshes, we can turn the monocular 3D shape reconstruction of a deformable surface given correspondences with a reference image into a much better-posed problem. This allows us to quickly and reliably eliminate outliers by simply solving a linear least squares problem. This yields an initial 3D shape estimate, which is not necessarily accurate, but whose 2D projections are. The initial shape is then refined by a constrained optimization problem to output the final surface reconstruction. Our approach allows us to reduce the dimensionality of the surface reconstruction problem without sacrificing accuracy, thus allowing for real-time implementations.</description><identifier>EISSN: 2331-8422</identifier><identifier>DOI: 10.48550/arxiv.1503.04643</identifier><language>eng</language><publisher>Ithaca: Cornell University Library, arXiv.org</publisher><subject>Computer Science - Computer Vision and Pattern Recognition ; Deformation ; Formability ; Image reconstruction ; Least squares method ; Optimization</subject><ispartof>arXiv.org, 2015-05</ispartof><rights>2015. This work is published under http://arxiv.org/licenses/nonexclusive-distrib/1.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.</rights><rights>http://arxiv.org/licenses/nonexclusive-distrib/1.0</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>228,230,780,784,885,27925</link.rule.ids><backlink>$$Uhttps://doi.org/10.1109/TPAMI.2015.2435739$$DView published paper (Access to full text may be restricted)$$Hfree_for_read</backlink><backlink>$$Uhttps://doi.org/10.48550/arXiv.1503.04643$$DView paper in arXiv$$Hfree_for_read</backlink></links><search><creatorcontrib>Dat Tien Ngo</creatorcontrib><creatorcontrib>Ostlund, Jonas</creatorcontrib><creatorcontrib>Fua, Pascal</creatorcontrib><title>Template-based Monocular 3D Shape Recovery using Laplacian Meshes</title><title>arXiv.org</title><description>We show that by extending the Laplacian formalism, which was first introduced in the Graphics community to regularize 3D meshes, we can turn the monocular 3D shape reconstruction of a deformable surface given correspondences with a reference image into a much better-posed problem. This allows us to quickly and reliably eliminate outliers by simply solving a linear least squares problem. This yields an initial 3D shape estimate, which is not necessarily accurate, but whose 2D projections are. The initial shape is then refined by a constrained optimization problem to output the final surface reconstruction. Our approach allows us to reduce the dimensionality of the surface reconstruction problem without sacrificing accuracy, thus allowing for real-time implementations.</description><subject>Computer Science - Computer Vision and Pattern Recognition</subject><subject>Deformation</subject><subject>Formability</subject><subject>Image reconstruction</subject><subject>Least squares method</subject><subject>Optimization</subject><issn>2331-8422</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2015</creationdate><recordtype>article</recordtype><sourceid>ABUWG</sourceid><sourceid>AFKRA</sourceid><sourceid>AZQEC</sourceid><sourceid>BENPR</sourceid><sourceid>CCPQU</sourceid><sourceid>DWQXO</sourceid><sourceid>GOX</sourceid><recordid>eNotj0tvgkAUhSdNmtRYf0BXnaRr6J0XDEtjHzbBNKnuyQUuFYNAZ8TUf1_Ubu7ZfOfkfow9CAi1NQae0f3Wx1AYUCHoSKsbNpFKicBqKe_YzPsdAMgolsaoCZtvaN83eKAgR08lX3VtVwwNOq5e-HqLPfEvKrojuRMffN1-8xRHvqix5SvyW_L37LbCxtPsP6ds_fa6WSyD9PP9YzFPAzRSBTnpCpUmgCgSNimpKKvERgSi0IQi12USkaTKAAqTJzLO5bmHMcQmya2assfr6kUv6129R3fKzprZRXMknq5E77qfgfwh23WDa8eXMglWqUTF4_0DnGtUWA</recordid><startdate>20150506</startdate><enddate>20150506</enddate><creator>Dat Tien Ngo</creator><creator>Ostlund, Jonas</creator><creator>Fua, Pascal</creator><general>Cornell University Library, arXiv.org</general><scope>8FE</scope><scope>8FG</scope><scope>ABJCF</scope><scope>ABUWG</scope><scope>AFKRA</scope><scope>AZQEC</scope><scope>BENPR</scope><scope>BGLVJ</scope><scope>CCPQU</scope><scope>DWQXO</scope><scope>HCIFZ</scope><scope>L6V</scope><scope>M7S</scope><scope>PIMPY</scope><scope>PQEST</scope><scope>PQQKQ</scope><scope>PQUKI</scope><scope>PRINS</scope><scope>PTHSS</scope><scope>AKY</scope><scope>GOX</scope></search><sort><creationdate>20150506</creationdate><title>Template-based Monocular 3D Shape Recovery using Laplacian Meshes</title><author>Dat Tien Ngo ; Ostlund, Jonas ; Fua, Pascal</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-a523-be4fa34e0066189decdf986e01c4ea1b4d96e2ef50a15b927b2a523a70759b83</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2015</creationdate><topic>Computer Science - Computer Vision and Pattern Recognition</topic><topic>Deformation</topic><topic>Formability</topic><topic>Image reconstruction</topic><topic>Least squares method</topic><topic>Optimization</topic><toplevel>online_resources</toplevel><creatorcontrib>Dat Tien Ngo</creatorcontrib><creatorcontrib>Ostlund, Jonas</creatorcontrib><creatorcontrib>Fua, Pascal</creatorcontrib><collection>ProQuest SciTech Collection</collection><collection>ProQuest Technology Collection</collection><collection>Materials Science &amp; Engineering Collection</collection><collection>ProQuest Central (Alumni)</collection><collection>ProQuest Central</collection><collection>ProQuest Central Essentials</collection><collection>AUTh Library subscriptions: ProQuest Central</collection><collection>Technology Collection</collection><collection>ProQuest One Community College</collection><collection>ProQuest Central</collection><collection>SciTech Premium Collection</collection><collection>ProQuest Engineering Collection</collection><collection>Engineering Database</collection><collection>Publicly Available Content Database (Proquest) (PQ_SDU_P3)</collection><collection>ProQuest One Academic Eastern Edition (DO NOT USE)</collection><collection>ProQuest One Academic</collection><collection>ProQuest One Academic UKI Edition</collection><collection>ProQuest Central China</collection><collection>Engineering Collection</collection><collection>arXiv Computer Science</collection><collection>arXiv.org</collection><jtitle>arXiv.org</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Dat Tien Ngo</au><au>Ostlund, Jonas</au><au>Fua, Pascal</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Template-based Monocular 3D Shape Recovery using Laplacian Meshes</atitle><jtitle>arXiv.org</jtitle><date>2015-05-06</date><risdate>2015</risdate><eissn>2331-8422</eissn><abstract>We show that by extending the Laplacian formalism, which was first introduced in the Graphics community to regularize 3D meshes, we can turn the monocular 3D shape reconstruction of a deformable surface given correspondences with a reference image into a much better-posed problem. This allows us to quickly and reliably eliminate outliers by simply solving a linear least squares problem. This yields an initial 3D shape estimate, which is not necessarily accurate, but whose 2D projections are. The initial shape is then refined by a constrained optimization problem to output the final surface reconstruction. Our approach allows us to reduce the dimensionality of the surface reconstruction problem without sacrificing accuracy, thus allowing for real-time implementations.</abstract><cop>Ithaca</cop><pub>Cornell University Library, arXiv.org</pub><doi>10.48550/arxiv.1503.04643</doi><oa>free_for_read</oa></addata></record>
fulltext fulltext
identifier EISSN: 2331-8422
ispartof arXiv.org, 2015-05
issn 2331-8422
language eng
recordid cdi_arxiv_primary_1503_04643
source arXiv.org; Open Access: Freely Accessible Journals by multiple vendors
subjects Computer Science - Computer Vision and Pattern Recognition
Deformation
Formability
Image reconstruction
Least squares method
Optimization
title Template-based Monocular 3D Shape Recovery using Laplacian Meshes
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-07T15%3A31%3A39IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_arxiv&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Template-based%20Monocular%203D%20Shape%20Recovery%20using%20Laplacian%20Meshes&rft.jtitle=arXiv.org&rft.au=Dat%20Tien%20Ngo&rft.date=2015-05-06&rft.eissn=2331-8422&rft_id=info:doi/10.48550/arxiv.1503.04643&rft_dat=%3Cproquest_arxiv%3E2083393783%3C/proquest_arxiv%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2083393783&rft_id=info:pmid/&rfr_iscdi=true