Enlightening Low-Light Images With Dynamic Guidance for Context Enrichment
Images acquired in low-light conditions suffer from a series of visual quality degradations, e.g. , low visibility, degraded contrast, and intensive noise. These complicated degradations based on various contexts ( e.g ., noise in smooth regions, over-exposure in well-exposed regions and low contras...
Gespeichert in:
Veröffentlicht in: | IEEE transactions on circuits and systems for video technology 2022-08, Vol.32 (8), p.5068-5079 |
---|---|
Hauptverfasser: | , , , , |
Format: | Artikel |
Sprache: | eng |
Schlagworte: | |
Online-Zugang: | Volltext bestellen |
Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
container_end_page | 5079 |
---|---|
container_issue | 8 |
container_start_page | 5068 |
container_title | IEEE transactions on circuits and systems for video technology |
container_volume | 32 |
creator | Zhu, Lingyu Yang, Wenhan Chen, Baoliang Lu, Fangbo Wang, Shiqi |
description | Images acquired in low-light conditions suffer from a series of visual quality degradations, e.g. , low visibility, degraded contrast, and intensive noise. These complicated degradations based on various contexts ( e.g ., noise in smooth regions, over-exposure in well-exposed regions and low contrast around edges) cast major challenges to the low-light image enhancement. Herein, we propose a new methodology by imposing a learnable guidance map from the signal and deep priors, making the deep neural network adaptively enhance low-light images in a region-dependent manner. The enhancement capability of the learnable guidance map is further exploited with the multi-scale dilated context collaboration, leading to contextually enriched feature representations extracted by the model with various receptive fields. Through assimilating the intrinsic perceptual information from the learned guidance map, richer and more realistic textures are generated. Extensive experiments on real low-light images demonstrate the effectiveness of our method, which delivers superior results quantitatively and qualitatively. The code is available at https://github.com/lingyzhu0101/GEMSC to facilitate future research. |
doi_str_mv | 10.1109/TCSVT.2022.3146731 |
format | Article |
fullrecord | <record><control><sourceid>proquest_RIE</sourceid><recordid>TN_cdi_ieee_primary_9693933</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>9693933</ieee_id><sourcerecordid>2697571658</sourcerecordid><originalsourceid>FETCH-LOGICAL-c295t-a35f050688ed1b54b24df9e0cb8f815157ceaa366487055c39fe2d5afe91138f3</originalsourceid><addsrcrecordid>eNo9kEFOwzAQRS0EEqVwAdhYYp3isTOJvUSllKJILCiwtFzHbl01TklSQW9PShGr-SP9NyM9Qq6BjQCYupuPX9_nI844HwlIs1zACRkAokw4Z3jaZ4aQSA54Ti7ads0YpDLNB-R5EjdhuepcDHFJi_orKQ4rnVVm6Vr6EboVfdhHUwVLp7tQmmgd9XVDx3Xs3HdHJ7EJdlW52F2SM282rbv6m0Py9jiZj5-S4mU6G98XieUKu8QI9AxZJqUrYYHpgqelV47ZhfQSEDC3zhiRZanMGaIVyjteovFOAQjpxZDcHu9um_pz59pOr-tdE_uXmmcqxxwylH2LH1u2qdu2cV5vm1CZZq-B6YMz_etMH5zpP2c9dHOEgnPuH1CZEkoI8QO7qWel</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2697571658</pqid></control><display><type>article</type><title>Enlightening Low-Light Images With Dynamic Guidance for Context Enrichment</title><source>IEEE Electronic Library (IEL)</source><creator>Zhu, Lingyu ; Yang, Wenhan ; Chen, Baoliang ; Lu, Fangbo ; Wang, Shiqi</creator><creatorcontrib>Zhu, Lingyu ; Yang, Wenhan ; Chen, Baoliang ; Lu, Fangbo ; Wang, Shiqi</creatorcontrib><description>Images acquired in low-light conditions suffer from a series of visual quality degradations, e.g. , low visibility, degraded contrast, and intensive noise. These complicated degradations based on various contexts ( e.g ., noise in smooth regions, over-exposure in well-exposed regions and low contrast around edges) cast major challenges to the low-light image enhancement. Herein, we propose a new methodology by imposing a learnable guidance map from the signal and deep priors, making the deep neural network adaptively enhance low-light images in a region-dependent manner. The enhancement capability of the learnable guidance map is further exploited with the multi-scale dilated context collaboration, leading to contextually enriched feature representations extracted by the model with various receptive fields. Through assimilating the intrinsic perceptual information from the learned guidance map, richer and more realistic textures are generated. Extensive experiments on real low-light images demonstrate the effectiveness of our method, which delivers superior results quantitatively and qualitatively. The code is available at https://github.com/lingyzhu0101/GEMSC to facilitate future research.</description><identifier>ISSN: 1051-8215</identifier><identifier>EISSN: 1558-2205</identifier><identifier>DOI: 10.1109/TCSVT.2022.3146731</identifier><identifier>CODEN: ITCTEM</identifier><language>eng</language><publisher>New York: IEEE</publisher><subject>Adaptation models ; Artificial neural networks ; Context ; contextual feature ; Degradation ; Feature extraction ; guidance map ; Histograms ; Image acquisition ; Image color analysis ; Image contrast ; Image edge detection ; Image enhancement ; Lighting ; Low visibility ; Low-light image enhancement</subject><ispartof>IEEE transactions on circuits and systems for video technology, 2022-08, Vol.32 (8), p.5068-5079</ispartof><rights>Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2022</rights><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c295t-a35f050688ed1b54b24df9e0cb8f815157ceaa366487055c39fe2d5afe91138f3</citedby><cites>FETCH-LOGICAL-c295t-a35f050688ed1b54b24df9e0cb8f815157ceaa366487055c39fe2d5afe91138f3</cites><orcidid>0000-0002-3583-959X ; 0000-0001-7608-7913 ; 0000-0003-4884-6956</orcidid></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://ieeexplore.ieee.org/document/9693933$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>314,780,784,796,27924,27925,54758</link.rule.ids><linktorsrc>$$Uhttps://ieeexplore.ieee.org/document/9693933$$EView_record_in_IEEE$$FView_record_in_$$GIEEE</linktorsrc></links><search><creatorcontrib>Zhu, Lingyu</creatorcontrib><creatorcontrib>Yang, Wenhan</creatorcontrib><creatorcontrib>Chen, Baoliang</creatorcontrib><creatorcontrib>Lu, Fangbo</creatorcontrib><creatorcontrib>Wang, Shiqi</creatorcontrib><title>Enlightening Low-Light Images With Dynamic Guidance for Context Enrichment</title><title>IEEE transactions on circuits and systems for video technology</title><addtitle>TCSVT</addtitle><description>Images acquired in low-light conditions suffer from a series of visual quality degradations, e.g. , low visibility, degraded contrast, and intensive noise. These complicated degradations based on various contexts ( e.g ., noise in smooth regions, over-exposure in well-exposed regions and low contrast around edges) cast major challenges to the low-light image enhancement. Herein, we propose a new methodology by imposing a learnable guidance map from the signal and deep priors, making the deep neural network adaptively enhance low-light images in a region-dependent manner. The enhancement capability of the learnable guidance map is further exploited with the multi-scale dilated context collaboration, leading to contextually enriched feature representations extracted by the model with various receptive fields. Through assimilating the intrinsic perceptual information from the learned guidance map, richer and more realistic textures are generated. Extensive experiments on real low-light images demonstrate the effectiveness of our method, which delivers superior results quantitatively and qualitatively. The code is available at https://github.com/lingyzhu0101/GEMSC to facilitate future research.</description><subject>Adaptation models</subject><subject>Artificial neural networks</subject><subject>Context</subject><subject>contextual feature</subject><subject>Degradation</subject><subject>Feature extraction</subject><subject>guidance map</subject><subject>Histograms</subject><subject>Image acquisition</subject><subject>Image color analysis</subject><subject>Image contrast</subject><subject>Image edge detection</subject><subject>Image enhancement</subject><subject>Lighting</subject><subject>Low visibility</subject><subject>Low-light image enhancement</subject><issn>1051-8215</issn><issn>1558-2205</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2022</creationdate><recordtype>article</recordtype><sourceid>RIE</sourceid><recordid>eNo9kEFOwzAQRS0EEqVwAdhYYp3isTOJvUSllKJILCiwtFzHbl01TklSQW9PShGr-SP9NyM9Qq6BjQCYupuPX9_nI844HwlIs1zACRkAokw4Z3jaZ4aQSA54Ti7ads0YpDLNB-R5EjdhuepcDHFJi_orKQ4rnVVm6Vr6EboVfdhHUwVLp7tQmmgd9XVDx3Xs3HdHJ7EJdlW52F2SM282rbv6m0Py9jiZj5-S4mU6G98XieUKu8QI9AxZJqUrYYHpgqelV47ZhfQSEDC3zhiRZanMGaIVyjteovFOAQjpxZDcHu9um_pz59pOr-tdE_uXmmcqxxwylH2LH1u2qdu2cV5vm1CZZq-B6YMz_etMH5zpP2c9dHOEgnPuH1CZEkoI8QO7qWel</recordid><startdate>20220801</startdate><enddate>20220801</enddate><creator>Zhu, Lingyu</creator><creator>Yang, Wenhan</creator><creator>Chen, Baoliang</creator><creator>Lu, Fangbo</creator><creator>Wang, Shiqi</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/0000-0002-3583-959X</orcidid><orcidid>https://orcid.org/0000-0001-7608-7913</orcidid><orcidid>https://orcid.org/0000-0003-4884-6956</orcidid></search><sort><creationdate>20220801</creationdate><title>Enlightening Low-Light Images With Dynamic Guidance for Context Enrichment</title><author>Zhu, Lingyu ; Yang, Wenhan ; Chen, Baoliang ; Lu, Fangbo ; Wang, Shiqi</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c295t-a35f050688ed1b54b24df9e0cb8f815157ceaa366487055c39fe2d5afe91138f3</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2022</creationdate><topic>Adaptation models</topic><topic>Artificial neural networks</topic><topic>Context</topic><topic>contextual feature</topic><topic>Degradation</topic><topic>Feature extraction</topic><topic>guidance map</topic><topic>Histograms</topic><topic>Image acquisition</topic><topic>Image color analysis</topic><topic>Image contrast</topic><topic>Image edge detection</topic><topic>Image enhancement</topic><topic>Lighting</topic><topic>Low visibility</topic><topic>Low-light image enhancement</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Zhu, Lingyu</creatorcontrib><creatorcontrib>Yang, Wenhan</creatorcontrib><creatorcontrib>Chen, Baoliang</creatorcontrib><creatorcontrib>Lu, Fangbo</creatorcontrib><creatorcontrib>Wang, Shiqi</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 & 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>Zhu, Lingyu</au><au>Yang, Wenhan</au><au>Chen, Baoliang</au><au>Lu, Fangbo</au><au>Wang, Shiqi</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Enlightening Low-Light Images With Dynamic Guidance for Context Enrichment</atitle><jtitle>IEEE transactions on circuits and systems for video technology</jtitle><stitle>TCSVT</stitle><date>2022-08-01</date><risdate>2022</risdate><volume>32</volume><issue>8</issue><spage>5068</spage><epage>5079</epage><pages>5068-5079</pages><issn>1051-8215</issn><eissn>1558-2205</eissn><coden>ITCTEM</coden><abstract>Images acquired in low-light conditions suffer from a series of visual quality degradations, e.g. , low visibility, degraded contrast, and intensive noise. These complicated degradations based on various contexts ( e.g ., noise in smooth regions, over-exposure in well-exposed regions and low contrast around edges) cast major challenges to the low-light image enhancement. Herein, we propose a new methodology by imposing a learnable guidance map from the signal and deep priors, making the deep neural network adaptively enhance low-light images in a region-dependent manner. The enhancement capability of the learnable guidance map is further exploited with the multi-scale dilated context collaboration, leading to contextually enriched feature representations extracted by the model with various receptive fields. Through assimilating the intrinsic perceptual information from the learned guidance map, richer and more realistic textures are generated. Extensive experiments on real low-light images demonstrate the effectiveness of our method, which delivers superior results quantitatively and qualitatively. The code is available at https://github.com/lingyzhu0101/GEMSC to facilitate future research.</abstract><cop>New York</cop><pub>IEEE</pub><doi>10.1109/TCSVT.2022.3146731</doi><tpages>12</tpages><orcidid>https://orcid.org/0000-0002-3583-959X</orcidid><orcidid>https://orcid.org/0000-0001-7608-7913</orcidid><orcidid>https://orcid.org/0000-0003-4884-6956</orcidid></addata></record> |
fulltext | fulltext_linktorsrc |
identifier | ISSN: 1051-8215 |
ispartof | IEEE transactions on circuits and systems for video technology, 2022-08, Vol.32 (8), p.5068-5079 |
issn | 1051-8215 1558-2205 |
language | eng |
recordid | cdi_ieee_primary_9693933 |
source | IEEE Electronic Library (IEL) |
subjects | Adaptation models Artificial neural networks Context contextual feature Degradation Feature extraction guidance map Histograms Image acquisition Image color analysis Image contrast Image edge detection Image enhancement Lighting Low visibility Low-light image enhancement |
title | Enlightening Low-Light Images With Dynamic Guidance for Context Enrichment |
url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-23T08%3A26%3A34IST&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=Enlightening%20Low-Light%20Images%20With%20Dynamic%20Guidance%20for%20Context%20Enrichment&rft.jtitle=IEEE%20transactions%20on%20circuits%20and%20systems%20for%20video%20technology&rft.au=Zhu,%20Lingyu&rft.date=2022-08-01&rft.volume=32&rft.issue=8&rft.spage=5068&rft.epage=5079&rft.pages=5068-5079&rft.issn=1051-8215&rft.eissn=1558-2205&rft.coden=ITCTEM&rft_id=info:doi/10.1109/TCSVT.2022.3146731&rft_dat=%3Cproquest_RIE%3E2697571658%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=2697571658&rft_id=info:pmid/&rft_ieee_id=9693933&rfr_iscdi=true |