Two-Layer Gaussian Process Regression With Example Selection for Image Dehazing

Researchers have devoted great efforts to image dehazing with prior assumptions in the past decade. Recently developed example-based approaches typically lack elegant models for the hazy process and meanwhile demand synthetic hazy images by manual selection. The priors from observations, and those t...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:IEEE transactions on circuits and systems for video technology 2017-12, Vol.27 (12), p.2505-2517
Hauptverfasser: Fan, Xin, Wang, Yi, Tang, Xianxuan, Gao, Renjie, Luo, Zhongxuan
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page 2517
container_issue 12
container_start_page 2505
container_title IEEE transactions on circuits and systems for video technology
container_volume 27
creator Fan, Xin
Wang, Yi
Tang, Xianxuan
Gao, Renjie
Luo, Zhongxuan
description Researchers have devoted great efforts to image dehazing with prior assumptions in the past decade. Recently developed example-based approaches typically lack elegant models for the hazy process and meanwhile demand synthetic hazy images by manual selection. The priors from observations, and those trained from synthetic images cannot always reflect true structural information of natural images in practice. In this paper, we present a learning model for haze removal by using two-layer Gaussian process regression (GPR). By using training examples, the two-layer GPR establishes a direct relationship from the input image to the depth-dependent transmission, and learns local image priors to further improve the estimation. We also provide a systematic scheme to automatically collect suitable training pairs, which works for both simulated examples and images of natural scenes. Both qualitative and quantitative comparisons on real-world and synthetic hazy images demonstrate the effectiveness of the proposed approach, especially for white or bright objects and heavy haze regions in which traditional methods may fail.
doi_str_mv 10.1109/TCSVT.2016.2592328
format Article
fullrecord <record><control><sourceid>proquest_RIE</sourceid><recordid>TN_cdi_ieee_primary_7514954</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>7514954</ieee_id><sourcerecordid>1977273628</sourcerecordid><originalsourceid>FETCH-LOGICAL-c295t-b0d2f261b5a6b3704944c5ca260132c9ab33978fd3d32173b340d2bcb57686573</originalsourceid><addsrcrecordid>eNo9kMFOAjEQhhujiYi-gF6aeF5sp-22PRoEJCHByKrHplu6sAR2sV2i-PQuQjz9k8n_zSQfQreU9Cgl-iHrz96zHhCa9kBoYKDOUIcKoRIAIs7bmQiaKKDiEl3FuCKEcsVlB02zrzqZ2L0PeGR3MZa2wi-hdj5G_OoXoc2yrvBH2Szx4NtutmuPZ37tXXNYF3XA441dePzkl_anrBbX6KKw6-hvTtlFb8NB1n9OJtPRuP84SRxo0SQ5mUMBKc2FTXMmCdecO-EspIQycNrmjGmpijmbM6CS5Yy3RO5yIVOVCsm66P54dxvqz52PjVnVu1C1Lw3VUoJkKai2BceWC3WMwRdmG8qNDXtDiTmIM3_izEGcOYlrobsjVHrv_wEpKNeCs1_JfWiv</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>1977273628</pqid></control><display><type>article</type><title>Two-Layer Gaussian Process Regression With Example Selection for Image Dehazing</title><source>IEEE Electronic Library (IEL)</source><creator>Fan, Xin ; Wang, Yi ; Tang, Xianxuan ; Gao, Renjie ; Luo, Zhongxuan</creator><creatorcontrib>Fan, Xin ; Wang, Yi ; Tang, Xianxuan ; Gao, Renjie ; Luo, Zhongxuan</creatorcontrib><description>Researchers have devoted great efforts to image dehazing with prior assumptions in the past decade. Recently developed example-based approaches typically lack elegant models for the hazy process and meanwhile demand synthetic hazy images by manual selection. The priors from observations, and those trained from synthetic images cannot always reflect true structural information of natural images in practice. In this paper, we present a learning model for haze removal by using two-layer Gaussian process regression (GPR). By using training examples, the two-layer GPR establishes a direct relationship from the input image to the depth-dependent transmission, and learns local image priors to further improve the estimation. We also provide a systematic scheme to automatically collect suitable training pairs, which works for both simulated examples and images of natural scenes. Both qualitative and quantitative comparisons on real-world and synthetic hazy images demonstrate the effectiveness of the proposed approach, especially for white or bright objects and heavy haze regions in which traditional methods may fail.</description><identifier>ISSN: 1051-8215</identifier><identifier>EISSN: 1558-2205</identifier><identifier>DOI: 10.1109/TCSVT.2016.2592328</identifier><identifier>CODEN: ITCTEM</identifier><language>eng</language><publisher>New York: IEEE</publisher><subject>Computational modeling ; Computer simulation ; Estimation ; Example selection ; Gaussian process ; Gaussian process regression (GPR) ; Gaussian processes ; Ground penetrating radar ; Haze ; image dehazing ; Image resolution ; Image restoration ; Image transmission ; Training</subject><ispartof>IEEE transactions on circuits and systems for video technology, 2017-12, Vol.27 (12), p.2505-2517</ispartof><rights>Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2017</rights><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c295t-b0d2f261b5a6b3704944c5ca260132c9ab33978fd3d32173b340d2bcb57686573</citedby><cites>FETCH-LOGICAL-c295t-b0d2f261b5a6b3704944c5ca260132c9ab33978fd3d32173b340d2bcb57686573</cites><orcidid>0000-0002-8991-4188</orcidid></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://ieeexplore.ieee.org/document/7514954$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>314,780,784,796,27924,27925,54758</link.rule.ids><linktorsrc>$$Uhttps://ieeexplore.ieee.org/document/7514954$$EView_record_in_IEEE$$FView_record_in_$$GIEEE</linktorsrc></links><search><creatorcontrib>Fan, Xin</creatorcontrib><creatorcontrib>Wang, Yi</creatorcontrib><creatorcontrib>Tang, Xianxuan</creatorcontrib><creatorcontrib>Gao, Renjie</creatorcontrib><creatorcontrib>Luo, Zhongxuan</creatorcontrib><title>Two-Layer Gaussian Process Regression With Example Selection for Image Dehazing</title><title>IEEE transactions on circuits and systems for video technology</title><addtitle>TCSVT</addtitle><description>Researchers have devoted great efforts to image dehazing with prior assumptions in the past decade. Recently developed example-based approaches typically lack elegant models for the hazy process and meanwhile demand synthetic hazy images by manual selection. The priors from observations, and those trained from synthetic images cannot always reflect true structural information of natural images in practice. In this paper, we present a learning model for haze removal by using two-layer Gaussian process regression (GPR). By using training examples, the two-layer GPR establishes a direct relationship from the input image to the depth-dependent transmission, and learns local image priors to further improve the estimation. We also provide a systematic scheme to automatically collect suitable training pairs, which works for both simulated examples and images of natural scenes. Both qualitative and quantitative comparisons on real-world and synthetic hazy images demonstrate the effectiveness of the proposed approach, especially for white or bright objects and heavy haze regions in which traditional methods may fail.</description><subject>Computational modeling</subject><subject>Computer simulation</subject><subject>Estimation</subject><subject>Example selection</subject><subject>Gaussian process</subject><subject>Gaussian process regression (GPR)</subject><subject>Gaussian processes</subject><subject>Ground penetrating radar</subject><subject>Haze</subject><subject>image dehazing</subject><subject>Image resolution</subject><subject>Image restoration</subject><subject>Image transmission</subject><subject>Training</subject><issn>1051-8215</issn><issn>1558-2205</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2017</creationdate><recordtype>article</recordtype><sourceid>RIE</sourceid><recordid>eNo9kMFOAjEQhhujiYi-gF6aeF5sp-22PRoEJCHByKrHplu6sAR2sV2i-PQuQjz9k8n_zSQfQreU9Cgl-iHrz96zHhCa9kBoYKDOUIcKoRIAIs7bmQiaKKDiEl3FuCKEcsVlB02zrzqZ2L0PeGR3MZa2wi-hdj5G_OoXoc2yrvBH2Szx4NtutmuPZ37tXXNYF3XA441dePzkl_anrBbX6KKw6-hvTtlFb8NB1n9OJtPRuP84SRxo0SQ5mUMBKc2FTXMmCdecO-EspIQycNrmjGmpijmbM6CS5Yy3RO5yIVOVCsm66P54dxvqz52PjVnVu1C1Lw3VUoJkKai2BceWC3WMwRdmG8qNDXtDiTmIM3_izEGcOYlrobsjVHrv_wEpKNeCs1_JfWiv</recordid><startdate>20171201</startdate><enddate>20171201</enddate><creator>Fan, Xin</creator><creator>Wang, Yi</creator><creator>Tang, Xianxuan</creator><creator>Gao, Renjie</creator><creator>Luo, Zhongxuan</creator><general>IEEE</general><general>The Institute of Electrical and Electronics Engineers, Inc. (IEEE)</general><scope>97E</scope><scope>RIA</scope><scope>RIE</scope><scope>AAYXX</scope><scope>CITATION</scope><scope>7SC</scope><scope>7SP</scope><scope>8FD</scope><scope>JQ2</scope><scope>L7M</scope><scope>L~C</scope><scope>L~D</scope><orcidid>https://orcid.org/0000-0002-8991-4188</orcidid></search><sort><creationdate>20171201</creationdate><title>Two-Layer Gaussian Process Regression With Example Selection for Image Dehazing</title><author>Fan, Xin ; Wang, Yi ; Tang, Xianxuan ; Gao, Renjie ; Luo, Zhongxuan</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c295t-b0d2f261b5a6b3704944c5ca260132c9ab33978fd3d32173b340d2bcb57686573</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2017</creationdate><topic>Computational modeling</topic><topic>Computer simulation</topic><topic>Estimation</topic><topic>Example selection</topic><topic>Gaussian process</topic><topic>Gaussian process regression (GPR)</topic><topic>Gaussian processes</topic><topic>Ground penetrating radar</topic><topic>Haze</topic><topic>image dehazing</topic><topic>Image resolution</topic><topic>Image restoration</topic><topic>Image transmission</topic><topic>Training</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Fan, Xin</creatorcontrib><creatorcontrib>Wang, Yi</creatorcontrib><creatorcontrib>Tang, Xianxuan</creatorcontrib><creatorcontrib>Gao, Renjie</creatorcontrib><creatorcontrib>Luo, Zhongxuan</creatorcontrib><collection>IEEE All-Society Periodicals Package (ASPP) 2005-present</collection><collection>IEEE All-Society Periodicals Package (ASPP) 1998-Present</collection><collection>IEEE Electronic Library (IEL)</collection><collection>CrossRef</collection><collection>Computer and Information Systems Abstracts</collection><collection>Electronics &amp; Communications Abstracts</collection><collection>Technology Research Database</collection><collection>ProQuest Computer Science Collection</collection><collection>Advanced Technologies Database with Aerospace</collection><collection>Computer and Information Systems Abstracts – Academic</collection><collection>Computer and Information Systems Abstracts Professional</collection><jtitle>IEEE transactions on circuits and systems for video technology</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Fan, Xin</au><au>Wang, Yi</au><au>Tang, Xianxuan</au><au>Gao, Renjie</au><au>Luo, Zhongxuan</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Two-Layer Gaussian Process Regression With Example Selection for Image Dehazing</atitle><jtitle>IEEE transactions on circuits and systems for video technology</jtitle><stitle>TCSVT</stitle><date>2017-12-01</date><risdate>2017</risdate><volume>27</volume><issue>12</issue><spage>2505</spage><epage>2517</epage><pages>2505-2517</pages><issn>1051-8215</issn><eissn>1558-2205</eissn><coden>ITCTEM</coden><abstract>Researchers have devoted great efforts to image dehazing with prior assumptions in the past decade. Recently developed example-based approaches typically lack elegant models for the hazy process and meanwhile demand synthetic hazy images by manual selection. The priors from observations, and those trained from synthetic images cannot always reflect true structural information of natural images in practice. In this paper, we present a learning model for haze removal by using two-layer Gaussian process regression (GPR). By using training examples, the two-layer GPR establishes a direct relationship from the input image to the depth-dependent transmission, and learns local image priors to further improve the estimation. We also provide a systematic scheme to automatically collect suitable training pairs, which works for both simulated examples and images of natural scenes. Both qualitative and quantitative comparisons on real-world and synthetic hazy images demonstrate the effectiveness of the proposed approach, especially for white or bright objects and heavy haze regions in which traditional methods may fail.</abstract><cop>New York</cop><pub>IEEE</pub><doi>10.1109/TCSVT.2016.2592328</doi><tpages>13</tpages><orcidid>https://orcid.org/0000-0002-8991-4188</orcidid></addata></record>
fulltext fulltext_linktorsrc
identifier ISSN: 1051-8215
ispartof IEEE transactions on circuits and systems for video technology, 2017-12, Vol.27 (12), p.2505-2517
issn 1051-8215
1558-2205
language eng
recordid cdi_ieee_primary_7514954
source IEEE Electronic Library (IEL)
subjects Computational modeling
Computer simulation
Estimation
Example selection
Gaussian process
Gaussian process regression (GPR)
Gaussian processes
Ground penetrating radar
Haze
image dehazing
Image resolution
Image restoration
Image transmission
Training
title Two-Layer Gaussian Process Regression With Example Selection for Image Dehazing
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-05T05%3A57%3A20IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_RIE&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Two-Layer%20Gaussian%20Process%20Regression%20With%20Example%20Selection%20for%20Image%20Dehazing&rft.jtitle=IEEE%20transactions%20on%20circuits%20and%20systems%20for%20video%20technology&rft.au=Fan,%20Xin&rft.date=2017-12-01&rft.volume=27&rft.issue=12&rft.spage=2505&rft.epage=2517&rft.pages=2505-2517&rft.issn=1051-8215&rft.eissn=1558-2205&rft.coden=ITCTEM&rft_id=info:doi/10.1109/TCSVT.2016.2592328&rft_dat=%3Cproquest_RIE%3E1977273628%3C/proquest_RIE%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=1977273628&rft_id=info:pmid/&rft_ieee_id=7514954&rfr_iscdi=true