Depth Estimation Through a Generative Model of Light Field Synthesis

Depth Estimation Through a Generative Model of Light Field Synthesis

Light field photography captures rich structural information that may facilitate a number of traditional image processing and computer vision tasks. A crucial ingredient in such endeavors is accurate depth recovery. We present a novel framework that allows the recovery of a high quality continuous d...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:arXiv.org 2016-09
Hauptverfasser: Sajjadi, Mehdi S M, Köhler, Rolf, Schölkopf, Bernhard, Hirsch, Michael
Format: Artikel
Sprache:eng
Schlagworte:
Computer Science - Computer Vision and Pattern Recognition
Computer Science - Graphics
Computer vision
Data recovery
Electrons
Image processing
Photography
Regularization
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 Sajjadi, Mehdi S M
Köhler, Rolf
Schölkopf, Bernhard
Hirsch, Michael
description Light field photography captures rich structural information that may facilitate a number of traditional image processing and computer vision tasks. A crucial ingredient in such endeavors is accurate depth recovery. We present a novel framework that allows the recovery of a high quality continuous depth map from light field data. To this end we propose a generative model of a light field that is fully parametrized by its corresponding depth map. The model allows for the integration of powerful regularization techniques such as a non-local means prior, facilitating accurate depth map estimation.
doi_str_mv 10.48550/arxiv.1609.01499
format Article
fullrecord <record><control><sourceid>proquest_arxiv</sourceid><recordid>TN_cdi_arxiv_primary_1609_01499</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2080572605</sourcerecordid><originalsourceid>FETCH-LOGICAL-a525-8b5a8384b343ab5fe61fbea1dda77f13f959f1720aee9c0d906d64dc4e759c013</originalsourceid><addsrcrecordid>eNotj01Lw0AYhBdBsNT-AE8ueE599yvJHqVfChEP5h423XeblJjE3aTYf29sPQ0zDMM8hDwwWMpUKXg2_qc-LVkMeglMan1DZlwIFqWS8zuyCOEIADxOuFJiRtZr7IeKbsJQf5mh7lqaV74bDxU1dIct-ik8IX3vLDa0czSrD9VAtzU2ln6e26HCUId7cutME3Dxr3OSbzf56jXKPnZvq5csMoqrKC2VSUUqSyGFKZXDmLkSDbPWJIljwmmlHUs4GES9B6shtrG0e4mJmjwTc_J4nb0gFr2fLvtz8YdaXFCnxtO10fvue8QwFMdu9O30qeCQgkp4DEr8AljMVjU</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2080572605</pqid></control><display><type>article</type><title>Depth Estimation Through a Generative Model of Light Field Synthesis</title><source>arXiv.org</source><source>Free E- Journals</source><creator>Sajjadi, Mehdi S M ; Köhler, Rolf ; Schölkopf, Bernhard ; Hirsch, Michael</creator><creatorcontrib>Sajjadi, Mehdi S M ; Köhler, Rolf ; Schölkopf, Bernhard ; Hirsch, Michael</creatorcontrib><description>Light field photography captures rich structural information that may facilitate a number of traditional image processing and computer vision tasks. A crucial ingredient in such endeavors is accurate depth recovery. We present a novel framework that allows the recovery of a high quality continuous depth map from light field data. To this end we propose a generative model of a light field that is fully parametrized by its corresponding depth map. The model allows for the integration of powerful regularization techniques such as a non-local means prior, facilitating accurate depth map estimation.</description><identifier>EISSN: 2331-8422</identifier><identifier>DOI: 10.48550/arxiv.1609.01499</identifier><language>eng</language><publisher>Ithaca: Cornell University Library, arXiv.org</publisher><subject>Computer Science - Computer Vision and Pattern Recognition ; Computer Science - Graphics ; Computer vision ; Data recovery ; Electrons ; Image processing ; Photography ; Regularization</subject><ispartof>arXiv.org, 2016-09</ispartof><rights>2016. 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/10.1007/978-3-319-45886-1_35$$DView published paper (Access to full text may be restricted)$$Hfree_for_read</backlink><backlink>$$Uhttps://doi.org/10.48550/arXiv.1609.01499$$DView paper in arXiv$$Hfree_for_read</backlink></links><search><creatorcontrib>Sajjadi, Mehdi S M</creatorcontrib><creatorcontrib>Köhler, Rolf</creatorcontrib><creatorcontrib>Schölkopf, Bernhard</creatorcontrib><creatorcontrib>Hirsch, Michael</creatorcontrib><title>Depth Estimation Through a Generative Model of Light Field Synthesis</title><title>arXiv.org</title><description>Light field photography captures rich structural information that may facilitate a number of traditional image processing and computer vision tasks. A crucial ingredient in such endeavors is accurate depth recovery. We present a novel framework that allows the recovery of a high quality continuous depth map from light field data. To this end we propose a generative model of a light field that is fully parametrized by its corresponding depth map. The model allows for the integration of powerful regularization techniques such as a non-local means prior, facilitating accurate depth map estimation.</description><subject>Computer Science - Computer Vision and Pattern Recognition</subject><subject>Computer Science - Graphics</subject><subject>Computer vision</subject><subject>Data recovery</subject><subject>Electrons</subject><subject>Image processing</subject><subject>Photography</subject><subject>Regularization</subject><issn>2331-8422</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2016</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>eNotj01Lw0AYhBdBsNT-AE8ueE599yvJHqVfChEP5h423XeblJjE3aTYf29sPQ0zDMM8hDwwWMpUKXg2_qc-LVkMeglMan1DZlwIFqWS8zuyCOEIADxOuFJiRtZr7IeKbsJQf5mh7lqaV74bDxU1dIct-ik8IX3vLDa0czSrD9VAtzU2ln6e26HCUId7cutME3Dxr3OSbzf56jXKPnZvq5csMoqrKC2VSUUqSyGFKZXDmLkSDbPWJIljwmmlHUs4GES9B6shtrG0e4mJmjwTc_J4nb0gFr2fLvtz8YdaXFCnxtO10fvue8QwFMdu9O30qeCQgkp4DEr8AljMVjU</recordid><startdate>20160906</startdate><enddate>20160906</enddate><creator>Sajjadi, Mehdi S M</creator><creator>Köhler, Rolf</creator><creator>Schölkopf, Bernhard</creator><creator>Hirsch, Michael</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>20160906</creationdate><title>Depth Estimation Through a Generative Model of Light Field Synthesis</title><author>Sajjadi, Mehdi S M ; Köhler, Rolf ; Schölkopf, Bernhard ; Hirsch, Michael</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-a525-8b5a8384b343ab5fe61fbea1dda77f13f959f1720aee9c0d906d64dc4e759c013</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2016</creationdate><topic>Computer Science - Computer Vision and Pattern Recognition</topic><topic>Computer Science - Graphics</topic><topic>Computer vision</topic><topic>Data recovery</topic><topic>Electrons</topic><topic>Image processing</topic><topic>Photography</topic><topic>Regularization</topic><toplevel>online_resources</toplevel><creatorcontrib>Sajjadi, Mehdi S M</creatorcontrib><creatorcontrib>Köhler, Rolf</creatorcontrib><creatorcontrib>Schölkopf, Bernhard</creatorcontrib><creatorcontrib>Hirsch, Michael</creatorcontrib><collection>ProQuest SciTech Collection</collection><collection>ProQuest Technology Collection</collection><collection>Materials Science &amp; Engineering Collection</collection><collection>ProQuest Central (Alumni Edition)</collection><collection>ProQuest Central UK/Ireland</collection><collection>ProQuest Central Essentials</collection><collection>ProQuest Central</collection><collection>Technology Collection</collection><collection>ProQuest One Community College</collection><collection>ProQuest Central Korea</collection><collection>SciTech Premium Collection</collection><collection>ProQuest Engineering Collection</collection><collection>Engineering Database</collection><collection>Publicly Available Content Database</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>Sajjadi, Mehdi S M</au><au>Köhler, Rolf</au><au>Schölkopf, Bernhard</au><au>Hirsch, Michael</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Depth Estimation Through a Generative Model of Light Field Synthesis</atitle><jtitle>arXiv.org</jtitle><date>2016-09-06</date><risdate>2016</risdate><eissn>2331-8422</eissn><abstract>Light field photography captures rich structural information that may facilitate a number of traditional image processing and computer vision tasks. A crucial ingredient in such endeavors is accurate depth recovery. We present a novel framework that allows the recovery of a high quality continuous depth map from light field data. To this end we propose a generative model of a light field that is fully parametrized by its corresponding depth map. The model allows for the integration of powerful regularization techniques such as a non-local means prior, facilitating accurate depth map estimation.</abstract><cop>Ithaca</cop><pub>Cornell University Library, arXiv.org</pub><doi>10.48550/arxiv.1609.01499</doi><oa>free_for_read</oa></addata></record>
fulltext fulltext
identifier EISSN: 2331-8422
ispartof arXiv.org, 2016-09
issn 2331-8422
language eng
recordid cdi_arxiv_primary_1609_01499
source arXiv.org; Free E- Journals
subjects Computer Science - Computer Vision and Pattern Recognition
Computer Science - Graphics
Computer vision
Data recovery
Electrons
Image processing
Photography
Regularization
title Depth Estimation Through a Generative Model of Light Field Synthesis
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-28T16%3A02%3A38IST&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=Depth%20Estimation%20Through%20a%20Generative%20Model%20of%20Light%20Field%20Synthesis&rft.jtitle=arXiv.org&rft.au=Sajjadi,%20Mehdi%20S%20M&rft.date=2016-09-06&rft.eissn=2331-8422&rft_id=info:doi/10.48550/arxiv.1609.01499&rft_dat=%3Cproquest_arxiv%3E2080572605%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=2080572605&rft_id=info:pmid/&rfr_iscdi=true