Adaptive Unfolding Total Variation Network for Low-Light Image Enhancement

Real-world low-light images suffer from two main degradations, namely, inevitable noise and poor visibility. Since the noise exhibits different levels, its estimation has been implemented in recent works when enhancing low-light images from raw Bayer space. When it comes to sRGB color space, the noi...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:Proceedings / IEEE International Conference on Computer Vision s. 4419 - 4428
Hlavní autori: Zheng, Chuanjun, Shi, Daming, Shi, Wentian
Médium: Konferenčný príspevok..
Jazyk:English
Vydavateľské údaje: IEEE 01.10.2021
Predmet:
ISSN:2380-7504
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Abstract Real-world low-light images suffer from two main degradations, namely, inevitable noise and poor visibility. Since the noise exhibits different levels, its estimation has been implemented in recent works when enhancing low-light images from raw Bayer space. When it comes to sRGB color space, the noise estimation becomes more complicated due to the effect of the image processing pipeline. Nevertheless, most existing enhancing algorithms in sRGB space only focus on the low visibility problem or suppress the noise under a hypothetical noise level, leading them impractical due to the lack of robustness. To address this issue, we propose an adaptive unfolding total variation network (UTVNet), which approximates the noise level from the real sRGB low-light image by learning the balancing parameter in the model-based denoising method with total variation regularization. Meanwhile, we learn the noise level map by unrolling the corresponding minimization process for providing the inferences of smoothness and fidelity constraints. Guided by the noise level map, our UTVNet can recover finer details and is more capable to suppress noise in real captured low-light scenes. Extensive experiments on real-world low-light images clearly demonstrate the superior performance of UTVNet over state-of-the-art methods.
AbstractList Real-world low-light images suffer from two main degradations, namely, inevitable noise and poor visibility. Since the noise exhibits different levels, its estimation has been implemented in recent works when enhancing low-light images from raw Bayer space. When it comes to sRGB color space, the noise estimation becomes more complicated due to the effect of the image processing pipeline. Nevertheless, most existing enhancing algorithms in sRGB space only focus on the low visibility problem or suppress the noise under a hypothetical noise level, leading them impractical due to the lack of robustness. To address this issue, we propose an adaptive unfolding total variation network (UTVNet), which approximates the noise level from the real sRGB low-light image by learning the balancing parameter in the model-based denoising method with total variation regularization. Meanwhile, we learn the noise level map by unrolling the corresponding minimization process for providing the inferences of smoothness and fidelity constraints. Guided by the noise level map, our UTVNet can recover finer details and is more capable to suppress noise in real captured low-light scenes. Extensive experiments on real-world low-light images clearly demonstrate the superior performance of UTVNet over state-of-the-art methods.
Author Shi, Daming
Zheng, Chuanjun
Shi, Wentian
Author_xml – sequence: 1
  givenname: Chuanjun
  surname: Zheng
  fullname: Zheng, Chuanjun
  email: zhengchuanjun2019@email.szu.edu.cn
  organization: Shenzhen University
– sequence: 2
  givenname: Daming
  surname: Shi
  fullname: Shi, Daming
  email: dshi@szu.edu.cn
  organization: Shenzhen University
– sequence: 3
  givenname: Wentian
  surname: Shi
  fullname: Shi, Wentian
  email: shiwentian2018@email.szu.edu.cn
  organization: Shenzhen University
BookMark eNotzstOAjEYQOFqNBGQJ9BFX2Dw771dkgkiZqIbYEtKL1CFlgyNxLfXRFdn9-UM0U0uOSD0SGBCCJinRduuuTaUTihQMgHgHK7Q2ChNpBScakLFNRpQpqFRAvgdGp7PHwDMUC0H6HXq7ammr4BXOZaDT3mHl6XaA17bPtmaSsZvoV5K_4lj6XFXLk2XdvuKF0e7C3iW9za7cAy53qPbaA_nMP7vCK2eZ8v2pene54t22jWJAqu_E4KayDhRxgnlXZQewGvh5FZrJ6SyzoAmPjLmQTpDIEpO5HarbPDSKTZCD39uCiFsTn062v57YxQBaSj7AZgXTwU
CODEN IEEPAD
ContentType Conference Proceeding
DBID 6IE
6IH
CBEJK
RIE
RIO
DOI 10.1109/ICCV48922.2021.00440
DatabaseName IEEE Electronic Library (IEL) Conference Proceedings
IEEE Proceedings Order Plan (POP) 1998-present by volume
IEEE Xplore All Conference Proceedings
IEEE Electronic Library (IEL)
IEEE Proceedings Order Plans (POP) 1998-present
DatabaseTitleList
Database_xml – sequence: 1
  dbid: RIE
  name: IEEE Electronic Library (IEL)
  url: https://ieeexplore.ieee.org/
  sourceTypes: Publisher
DeliveryMethod fulltext_linktorsrc
Discipline Applied Sciences
EISBN 9781665428125
1665428120
EISSN 2380-7504
EndPage 4428
ExternalDocumentID 9710692
Genre orig-research
GrantInformation_xml – fundername: Ministry of Science and Technology
  funderid: 10.13039/501100003711
GroupedDBID 29O
6IE
6IF
6IH
6IK
6IL
6IM
6IN
AAJGR
AAWTH
ACGFS
ADZIZ
ALMA_UNASSIGNED_HOLDINGS
BEFXN
BFFAM
BGNUA
BKEBE
BPEOZ
CBEJK
CHZPO
IPLJI
M43
OCL
RIE
RIL
RIO
RNS
ID FETCH-LOGICAL-i203t-75529f34179c57dcf6d00d85c6b88c567ac9081df33d06c910f6416bb7aed6c73
IEDL.DBID RIE
ISICitedReferencesCount 102
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000797698904063&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
IngestDate Wed Aug 27 02:25:36 EDT 2025
IsPeerReviewed false
IsScholarly true
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-i203t-75529f34179c57dcf6d00d85c6b88c567ac9081df33d06c910f6416bb7aed6c73
PageCount 10
ParticipantIDs ieee_primary_9710692
PublicationCentury 2000
PublicationDate 2021-Oct.
PublicationDateYYYYMMDD 2021-10-01
PublicationDate_xml – month: 10
  year: 2021
  text: 2021-Oct.
PublicationDecade 2020
PublicationTitle Proceedings / IEEE International Conference on Computer Vision
PublicationTitleAbbrev ICCV
PublicationYear 2021
Publisher IEEE
Publisher_xml – name: IEEE
SSID ssj0039286
Score 2.5407865
Snippet Real-world low-light images suffer from two main degradations, namely, inevitable noise and poor visibility. Since the noise exhibits different levels, its...
SourceID ieee
SourceType Publisher
StartPage 4419
SubjectTerms Adaptation models
Adaptive systems
Estimation
Low-level and physics-based vision
Minimization
Noise reduction
Pipelines
Title Adaptive Unfolding Total Variation Network for Low-Light Image Enhancement
URI https://ieeexplore.ieee.org/document/9710692
WOSCitedRecordID wos000797698904063&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV07T8MwELYKYmAq0CLe8sBI2sSOXyOqWlFUVR3aqlsVPyI6kFR9wN_n7IQiJBa2yEuss---z777fAg9GgBpof2Ts4m_ugF3iiRN0iixaUZi5rSKdWg2IcZjuVioSQM9HbQwzrlQfOY6_jPk8m1p9v6qrKsADrmCgHskBK-0Wt9RF2Be8loal8SqO-z15qlUxGutSNIJnZV_NVAJ-DFo_u_PZ6j9I8TDkwPEnKOGKy5Qs2aOuPbLbQu9Ptts7QMXnsGGCfkkPC2BV-M5nIWD8fG4KvjGwFLxqPyMRv5YjofvEFBwv3jzq-8n0UazQX_ae4nqLgnRisR0FwnGiMqp7yRmmLAm5zaOrWSGaykN4yIzCnDf5pTamBugBzkHFqa1yJzlRtBLdFyUhbtCODUpsdxnShlJtWaaCpcQ8FjjWAbM4hq1vGmW6-ohjGVtlZu_h2_Rqbd9Vfl2h453m727RyfmY7fabh7C6n0B1UWZwg
linkProvider IEEE
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV07T8MwELaqggRTgRbxxgMjaR3Hj3hEVasWQtShrbpV8aOiA0nVB_x9bCcUIbGwRVli3eXu--y78wfAg7IgzaW7cjZ0Rzc2nII4CkkQapJhRI0USHqxCZ6m8WwmRjXwuJ-FMcb45jPTdo--lq8LtXNHZR1h4ZAJm3APKCEYldNa33nXAn3MquG4EInOsNudklhgN22Fw7bXVv4loeIRpN_437dPQOtnFA-O9iBzCmomPwONijvCKjI3TfD8pLOVS11wYn8ZX1GC48Iyazi1u2FvfpiWLd_Q8lSYFJ9B4jbmcPhuUwrs5W_O_24RLTDp98bdQVDpJARLjKJtwCnFYhE5LTFFuVYLphHSMVVMxrGijGdKWOTXiyjSiClLEBbM8jApeWY0Uzw6B_W8yM0FgEQRrJmrlVJMpKQy4ibENmaVoZnlFpeg6UwzX5VXYcwrq1z9_foeHA3Gr8k8GaYv1-DY-aHsg7sB9e16Z27BofrYLjfrO-_JLwVynQk
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Abook&rft.genre=proceeding&rft.title=Proceedings+%2F+IEEE+International+Conference+on+Computer+Vision&rft.atitle=Adaptive+Unfolding+Total+Variation+Network+for+Low-Light+Image+Enhancement&rft.au=Zheng%2C+Chuanjun&rft.au=Shi%2C+Daming&rft.au=Shi%2C+Wentian&rft.date=2021-10-01&rft.pub=IEEE&rft.eissn=2380-7504&rft.spage=4419&rft.epage=4428&rft_id=info:doi/10.1109%2FICCV48922.2021.00440&rft.externalDocID=9710692