Pyramid Diffusion Models For Low-light Image Enhancement

Recovering noise-covered details from low-light images is challenging, and the results given by previous methods leave room for improvement. Recent diffusion models show realistic and detailed image generation through a sequence of denoising refinements and motivate us to introduce them to low-light...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:arXiv.org 2023-05
Hauptverfasser: Zhou, Dewei, Yang, Zongxin, Yang, Yi
Format: Artikel
Sprache:eng
Schlagworte:
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 Zhou, Dewei
Yang, Zongxin
Yang, Yi
description Recovering noise-covered details from low-light images is challenging, and the results given by previous methods leave room for improvement. Recent diffusion models show realistic and detailed image generation through a sequence of denoising refinements and motivate us to introduce them to low-light image enhancement for recovering realistic details. However, we found two problems when doing this, i.e., 1) diffusion models keep constant resolution in one reverse process, which limits the speed; 2) diffusion models sometimes result in global degradation (e.g., RGB shift). To address the above problems, this paper proposes a Pyramid Diffusion model (PyDiff) for low-light image enhancement. PyDiff uses a novel pyramid diffusion method to perform sampling in a pyramid resolution style (i.e., progressively increasing resolution in one reverse process). Pyramid diffusion makes PyDiff much faster than vanilla diffusion models and introduces no performance degradation. Furthermore, PyDiff uses a global corrector to alleviate the global degradation that may occur in the reverse process, significantly improving the performance and making the training of diffusion models easier with little additional computational consumption. Extensive experiments on popular benchmarks show that PyDiff achieves superior performance and efficiency. Moreover, PyDiff can generalize well to unseen noise and illumination distributions.
format Article
fullrecord <record><control><sourceid>proquest</sourceid><recordid>TN_cdi_proquest_journals_2815044398</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2815044398</sourcerecordid><originalsourceid>FETCH-proquest_journals_28150443983</originalsourceid><addsrcrecordid>eNpjYuA0MjY21LUwMTLiYOAtLs4yMDAwMjM3MjU15mSwCKgsSszNTFFwyUxLKy3OzM9T8M1PSc0pVnDLL1LwyS_XzclMzyhR8MxNTE9VcM3LSMxLTs1NzSvhYWBNS8wpTuWF0twMym6uIc4eugVF-YWlqcUl8Vn5pUV5QKl4IwtDUwMTE2NLC2PiVAEADDk1nQ</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2815044398</pqid></control><display><type>article</type><title>Pyramid Diffusion Models For Low-light Image Enhancement</title><source>Free E- Journals</source><creator>Zhou, Dewei ; Yang, Zongxin ; Yang, Yi</creator><creatorcontrib>Zhou, Dewei ; Yang, Zongxin ; Yang, Yi</creatorcontrib><description>Recovering noise-covered details from low-light images is challenging, and the results given by previous methods leave room for improvement. Recent diffusion models show realistic and detailed image generation through a sequence of denoising refinements and motivate us to introduce them to low-light image enhancement for recovering realistic details. However, we found two problems when doing this, i.e., 1) diffusion models keep constant resolution in one reverse process, which limits the speed; 2) diffusion models sometimes result in global degradation (e.g., RGB shift). To address the above problems, this paper proposes a Pyramid Diffusion model (PyDiff) for low-light image enhancement. PyDiff uses a novel pyramid diffusion method to perform sampling in a pyramid resolution style (i.e., progressively increasing resolution in one reverse process). Pyramid diffusion makes PyDiff much faster than vanilla diffusion models and introduces no performance degradation. Furthermore, PyDiff uses a global corrector to alleviate the global degradation that may occur in the reverse process, significantly improving the performance and making the training of diffusion models easier with little additional computational consumption. Extensive experiments on popular benchmarks show that PyDiff achieves superior performance and efficiency. Moreover, PyDiff can generalize well to unseen noise and illumination distributions.</description><identifier>EISSN: 2331-8422</identifier><language>eng</language><publisher>Ithaca: Cornell University Library, arXiv.org</publisher><subject>Diffusion rate ; Image enhancement ; Image processing ; Performance degradation</subject><ispartof>arXiv.org, 2023-05</ispartof><rights>2023. 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><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>780,784</link.rule.ids></links><search><creatorcontrib>Zhou, Dewei</creatorcontrib><creatorcontrib>Yang, Zongxin</creatorcontrib><creatorcontrib>Yang, Yi</creatorcontrib><title>Pyramid Diffusion Models For Low-light Image Enhancement</title><title>arXiv.org</title><description>Recovering noise-covered details from low-light images is challenging, and the results given by previous methods leave room for improvement. Recent diffusion models show realistic and detailed image generation through a sequence of denoising refinements and motivate us to introduce them to low-light image enhancement for recovering realistic details. However, we found two problems when doing this, i.e., 1) diffusion models keep constant resolution in one reverse process, which limits the speed; 2) diffusion models sometimes result in global degradation (e.g., RGB shift). To address the above problems, this paper proposes a Pyramid Diffusion model (PyDiff) for low-light image enhancement. PyDiff uses a novel pyramid diffusion method to perform sampling in a pyramid resolution style (i.e., progressively increasing resolution in one reverse process). Pyramid diffusion makes PyDiff much faster than vanilla diffusion models and introduces no performance degradation. Furthermore, PyDiff uses a global corrector to alleviate the global degradation that may occur in the reverse process, significantly improving the performance and making the training of diffusion models easier with little additional computational consumption. Extensive experiments on popular benchmarks show that PyDiff achieves superior performance and efficiency. Moreover, PyDiff can generalize well to unseen noise and illumination distributions.</description><subject>Diffusion rate</subject><subject>Image enhancement</subject><subject>Image processing</subject><subject>Performance degradation</subject><issn>2331-8422</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2023</creationdate><recordtype>article</recordtype><sourceid>ABUWG</sourceid><sourceid>AFKRA</sourceid><sourceid>AZQEC</sourceid><sourceid>BENPR</sourceid><sourceid>CCPQU</sourceid><sourceid>DWQXO</sourceid><recordid>eNpjYuA0MjY21LUwMTLiYOAtLs4yMDAwMjM3MjU15mSwCKgsSszNTFFwyUxLKy3OzM9T8M1PSc0pVnDLL1LwyS_XzclMzyhR8MxNTE9VcM3LSMxLTs1NzSvhYWBNS8wpTuWF0twMym6uIc4eugVF-YWlqcUl8Vn5pUV5QKl4IwtDUwMTE2NLC2PiVAEADDk1nQ</recordid><startdate>20230517</startdate><enddate>20230517</enddate><creator>Zhou, Dewei</creator><creator>Yang, Zongxin</creator><creator>Yang, Yi</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></search><sort><creationdate>20230517</creationdate><title>Pyramid Diffusion Models For Low-light Image Enhancement</title><author>Zhou, Dewei ; Yang, Zongxin ; Yang, Yi</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-proquest_journals_28150443983</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2023</creationdate><topic>Diffusion rate</topic><topic>Image enhancement</topic><topic>Image processing</topic><topic>Performance degradation</topic><toplevel>online_resources</toplevel><creatorcontrib>Zhou, Dewei</creatorcontrib><creatorcontrib>Yang, Zongxin</creatorcontrib><creatorcontrib>Yang, Yi</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></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Zhou, Dewei</au><au>Yang, Zongxin</au><au>Yang, Yi</au><format>book</format><genre>document</genre><ristype>GEN</ristype><atitle>Pyramid Diffusion Models For Low-light Image Enhancement</atitle><jtitle>arXiv.org</jtitle><date>2023-05-17</date><risdate>2023</risdate><eissn>2331-8422</eissn><abstract>Recovering noise-covered details from low-light images is challenging, and the results given by previous methods leave room for improvement. Recent diffusion models show realistic and detailed image generation through a sequence of denoising refinements and motivate us to introduce them to low-light image enhancement for recovering realistic details. However, we found two problems when doing this, i.e., 1) diffusion models keep constant resolution in one reverse process, which limits the speed; 2) diffusion models sometimes result in global degradation (e.g., RGB shift). To address the above problems, this paper proposes a Pyramid Diffusion model (PyDiff) for low-light image enhancement. PyDiff uses a novel pyramid diffusion method to perform sampling in a pyramid resolution style (i.e., progressively increasing resolution in one reverse process). Pyramid diffusion makes PyDiff much faster than vanilla diffusion models and introduces no performance degradation. Furthermore, PyDiff uses a global corrector to alleviate the global degradation that may occur in the reverse process, significantly improving the performance and making the training of diffusion models easier with little additional computational consumption. Extensive experiments on popular benchmarks show that PyDiff achieves superior performance and efficiency. Moreover, PyDiff can generalize well to unseen noise and illumination distributions.</abstract><cop>Ithaca</cop><pub>Cornell University Library, arXiv.org</pub><oa>free_for_read</oa></addata></record>
fulltext fulltext
identifier EISSN: 2331-8422
ispartof arXiv.org, 2023-05
issn 2331-8422
language eng
recordid cdi_proquest_journals_2815044398
source Free E- Journals
subjects Diffusion rate
Image enhancement
Image processing
Performance degradation
title Pyramid Diffusion Models For Low-light Image Enhancement
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-23T05%3A04%3A40IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest&rft_val_fmt=info:ofi/fmt:kev:mtx:book&rft.genre=document&rft.atitle=Pyramid%20Diffusion%20Models%20For%20Low-light%20Image%20Enhancement&rft.jtitle=arXiv.org&rft.au=Zhou,%20Dewei&rft.date=2023-05-17&rft.eissn=2331-8422&rft_id=info:doi/&rft_dat=%3Cproquest%3E2815044398%3C/proquest%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2815044398&rft_id=info:pmid/&rfr_iscdi=true