Sparse Gradient Regularized Deep Retinex Network for Robust Low-Light Image Enhancement

Due to the absence of a desirable objective for low-light image enhancement, previous data-driven methods may provide undesirable enhanced results including amplified noise, degraded contrast and biased colors. In this work, inspired by Retinex theory, we design an end-to-end signal prior-guided lay...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:IEEE transactions on image processing Jg. 30; S. 1
Hauptverfasser: Yang, Wenhan, Wang, Wenjing, Huang, Haofeng, Wanga, Shiqi, Liu, Jiaying
Format: Journal Article
Sprache:Englisch
Veröffentlicht: United States IEEE 01.01.2021
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Schlagworte:
ISSN:1057-7149, 1941-0042, 1941-0042
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Abstract Due to the absence of a desirable objective for low-light image enhancement, previous data-driven methods may provide undesirable enhanced results including amplified noise, degraded contrast and biased colors. In this work, inspired by Retinex theory, we design an end-to-end signal prior-guided layer separation and data-driven mapping network with layer-specified constraints for single-image low-light enhancement. A Sparse Gradient Minimization sub-Network (SGM-Net) is constructed to remove the low-amplitude structures and preserve major edge information, which facilitates extracting paired illumination maps of low/normal-light images. After the learned decomposition, two sub-networks (Enhance-Net and Restore-Net) are utilized to predict the enhanced illumination and reflectance maps, respectively, which helps stretch the contrast of the illumination map and remove intensive noise in the reflectance map. The effects of all these configured constraints, including the signal structure regularization and losses, combine together reciprocally, which leads to good reconstruction results in overall visual quality. The evaluation on both synthetic and real images, particularly on those containing intensive noise, compression artifacts and their interleaved artifacts, shows the effectiveness of our novel models, which significantly outperforms the state-of-the-art methods.
AbstractList Due to the absence of a desirable objective for low-light image enhancement, previous data-driven methods may provide undesirable enhanced results including amplified noise, degraded contrast and biased colors. In this work, inspired by Retinex theory, we design an end-to-end signal prior-guided layer separation and data-driven mapping network with layer-specified constraints for single-image low-light enhancement. A Sparse Gradient Minimization sub-Network (SGM-Net) is constructed to remove the low-amplitude structures and preserve major edge information, which facilitates extracting paired illumination maps of low/normal-light images. After the learned decomposition, two sub-networks (Enhance-Net and Restore-Net) are utilized to predict the enhanced illumination and reflectance maps, respectively, which helps stretch the contrast of the illumination map and remove intensive noise in the reflectance map. The effects of all these configured constraints, including the signal structure regularization and losses, combine together reciprocally, which leads to good reconstruction results in overall visual quality. The evaluation on both synthetic and real images, particularly on those containing intensive noise, compression artifacts and their interleaved artifacts, shows the effectiveness of our novel models, which significantly outperforms the state-of-the-art methods.Due to the absence of a desirable objective for low-light image enhancement, previous data-driven methods may provide undesirable enhanced results including amplified noise, degraded contrast and biased colors. In this work, inspired by Retinex theory, we design an end-to-end signal prior-guided layer separation and data-driven mapping network with layer-specified constraints for single-image low-light enhancement. A Sparse Gradient Minimization sub-Network (SGM-Net) is constructed to remove the low-amplitude structures and preserve major edge information, which facilitates extracting paired illumination maps of low/normal-light images. After the learned decomposition, two sub-networks (Enhance-Net and Restore-Net) are utilized to predict the enhanced illumination and reflectance maps, respectively, which helps stretch the contrast of the illumination map and remove intensive noise in the reflectance map. The effects of all these configured constraints, including the signal structure regularization and losses, combine together reciprocally, which leads to good reconstruction results in overall visual quality. The evaluation on both synthetic and real images, particularly on those containing intensive noise, compression artifacts and their interleaved artifacts, shows the effectiveness of our novel models, which significantly outperforms the state-of-the-art methods.
Due to the absence of a desirable objective for low-light image enhancement, previous data-driven methods may provide undesirable enhanced results including amplified noise, degraded contrast and biased colors. In this work, inspired by Retinex theory, we design an end-to-end signal prior-guided layer separation and data-driven mapping network with layer-specified constraints for single-image low-light enhancement. A Sparse Gradient Minimization sub-Network (SGM-Net) is constructed to remove the low-amplitude structures and preserve major edge information, which facilitates extracting paired illumination maps of low/normal-light images. After the learned decomposition, two sub-networks (Enhance-Net and Restore-Net) are utilized to predict the enhanced illumination and reflectance maps, respectively, which helps stretch the contrast of the illumination map and remove intensive noise in the reflectance map. The effects of all these configured constraints, including the signal structure regularization and losses, combine together reciprocally, which leads to good reconstruction results in overall visual quality. The evaluation on both synthetic and real images, particularly on those containing intensive noise, compression artifacts and their interleaved artifacts, shows the effectiveness of our novel models, which significantly outperforms the state-of-the-art methods.
Author Wang, Wenjing
Huang, Haofeng
Liu, Jiaying
Wanga, Shiqi
Yang, Wenhan
Author_xml – sequence: 1
  givenname: Wenhan
  surname: Yang
  fullname: Yang, Wenhan
– sequence: 2
  givenname: Wenjing
  surname: Wang
  fullname: Wang, Wenjing
– sequence: 3
  givenname: Haofeng
  surname: Huang
  fullname: Huang, Haofeng
– sequence: 4
  givenname: Shiqi
  surname: Wanga
  fullname: Wanga, Shiqi
– sequence: 5
  givenname: Jiaying
  surname: Liu
  fullname: Liu, Jiaying
BackLink https://www.ncbi.nlm.nih.gov/pubmed/33460379$$D View this record in MEDLINE/PubMed
BookMark eNp9kc1v1DAQxS1URL-4IyGhSFx6yTK2Z5P4iEpbVloB6od6tJxkduuS2IvtqMBfj8tuOfTAZTyyfu_pad4h23PeEWNvOMw4B_XhevFtJkDwmYQ5NHN4wQ64Ql4CoNjLO8zrsuao9tlhjPcAHOe8esX2pcQKZK0O2O3VxoRIxUUwvSWXiktaT4MJ9jf1xSeiTf5I1tHP4gulBx--FysfikvfTjEVS_9QLu36LhWL0aypOHN3xnU0Zp9j9nJlhkivd-8Ruzk_uz79XC6_XixOPy7LTmKdyr4zPaJQAlGJFtFUILDFqjP139kqjm1rlODNChtBDYFoK1QgqCaUII_YydZ3E_yPiWLSo40dDYNx5KeoBdYqH0PWMqPvn6H3fgoup8tUA02VMzSZerejpnakXm-CHU34pZ9OloFqC3TBxxhopTubTLLepWDsoDnox2507kY_dqN33WQhPBM-ef9H8nYrsUT0D1dSNDwn-QMeK5b3
CODEN IIPRE4
CitedBy_id crossref_primary_10_1145_3750732
crossref_primary_10_1038_s41598_025_10779_4
crossref_primary_10_1109_TPAMI_2024_3432308
crossref_primary_10_1016_j_engappai_2025_110981
crossref_primary_10_1016_j_eswa_2025_129436
crossref_primary_10_1016_j_heliyon_2023_e14558
crossref_primary_10_1049_ipr2_13259
crossref_primary_10_1016_j_patcog_2024_111180
crossref_primary_10_1109_TIM_2024_3375967
crossref_primary_10_1007_s00371_024_03636_4
crossref_primary_10_1007_s11063_023_11303_3
crossref_primary_10_3788_IRLA20240376
crossref_primary_10_1016_j_engappai_2024_109906
crossref_primary_10_1016_j_neucom_2025_131383
crossref_primary_10_1109_TIM_2022_3165303
crossref_primary_10_1016_j_patcog_2025_112421
crossref_primary_10_1109_TMM_2023_3293736
crossref_primary_10_1016_j_aei_2025_103463
crossref_primary_10_1016_j_jvcir_2024_104127
crossref_primary_10_1109_ACCESS_2025_3565727
crossref_primary_10_1109_ACCESS_2024_3403452
crossref_primary_10_1007_s11042_025_21051_2
crossref_primary_10_1109_TCSVT_2024_3519352
crossref_primary_10_1016_j_imavis_2024_105149
crossref_primary_10_1049_ell2_12755
crossref_primary_10_1109_TPAMI_2021_3126387
crossref_primary_10_1007_s11760_025_04004_y
crossref_primary_10_1016_j_patcog_2024_111074
crossref_primary_10_1016_j_eswa_2025_127263
crossref_primary_10_1016_j_image_2023_117060
crossref_primary_10_1016_j_neucom_2025_129980
crossref_primary_10_1016_j_patcog_2024_111076
crossref_primary_10_32604_cmc_2024_057662
crossref_primary_10_1007_s11760_024_03127_y
crossref_primary_10_1002_rob_22595
crossref_primary_10_1007_s00371_025_03875_z
crossref_primary_10_1049_ipr2_12750
crossref_primary_10_1016_j_isprsjprs_2025_06_011
crossref_primary_10_3390_app12147268
crossref_primary_10_1109_JSEN_2024_3396195
crossref_primary_10_1007_s11042_024_19720_9
crossref_primary_10_1109_TIM_2024_3353285
crossref_primary_10_1145_3700136
crossref_primary_10_3390_s24092711
crossref_primary_10_1007_s00530_025_01935_x
crossref_primary_10_1016_j_inffus_2022_12_012
crossref_primary_10_1007_s00034_023_02591_0
crossref_primary_10_1007_s11760_025_03918_x
crossref_primary_10_3390_s24155019
crossref_primary_10_1109_TCSVT_2025_3541429
crossref_primary_10_1016_j_cag_2022_12_001
crossref_primary_10_1109_TMM_2024_3407656
crossref_primary_10_1007_s00521_024_09779_8
crossref_primary_10_1109_TMM_2024_3414328
crossref_primary_10_1109_TCSVT_2024_3520802
crossref_primary_10_1016_j_image_2024_117222
crossref_primary_10_1109_TCSVT_2024_3483191
crossref_primary_10_3390_s25175521
crossref_primary_10_1145_3618373
crossref_primary_10_1016_j_neucom_2024_128974
crossref_primary_10_1007_s11263_025_02551_y
crossref_primary_10_1016_j_engappai_2025_111501
crossref_primary_10_1007_s00530_024_01581_9
crossref_primary_10_1016_j_imavis_2023_104813
crossref_primary_10_1109_LSP_2025_3562822
crossref_primary_10_1109_TCSVT_2024_3408007
crossref_primary_10_3390_e26030184
crossref_primary_10_1109_TIM_2023_3301049
crossref_primary_10_1109_TCE_2024_3516366
crossref_primary_10_1016_j_optlastec_2025_113810
crossref_primary_10_1109_TCE_2025_3572099
crossref_primary_10_1016_j_cag_2023_12_014
crossref_primary_10_1016_j_compind_2025_104314
crossref_primary_10_1109_TNNLS_2023_3280037
crossref_primary_10_1007_s10489_024_05534_7
crossref_primary_10_1007_s11760_025_04537_2
crossref_primary_10_1016_j_neucom_2025_130937
crossref_primary_10_1016_j_compeleceng_2024_109310
crossref_primary_10_1109_TCI_2025_3564112
crossref_primary_10_1145_3758097
crossref_primary_10_1007_s11263_025_02542_z
crossref_primary_10_1016_j_patcog_2025_112073
crossref_primary_10_1016_j_knosys_2025_114420
crossref_primary_10_3390_s22186799
crossref_primary_10_3390_sym17050798
crossref_primary_10_1016_j_patcog_2024_111033
crossref_primary_10_1016_j_cag_2022_04_002
crossref_primary_10_1007_s00371_024_03262_0
crossref_primary_10_1109_TIP_2025_3553070
crossref_primary_10_1007_s11263_024_02084_w
crossref_primary_10_1016_j_apm_2022_11_022
crossref_primary_10_1109_TPAMI_2025_3562211
crossref_primary_10_1109_TCSVT_2024_3465670
crossref_primary_10_1007_s44443_025_00167_3
crossref_primary_10_1016_j_ins_2022_07_051
crossref_primary_10_3390_app14146320
crossref_primary_10_1007_s00530_025_01928_w
crossref_primary_10_3390_photonics10020198
crossref_primary_10_1109_TCSVT_2023_3284856
crossref_primary_10_1109_JPHOT_2025_3541426
crossref_primary_10_1109_TIM_2025_3557114
crossref_primary_10_1016_j_neucom_2025_130005
crossref_primary_10_3390_electronics13101814
crossref_primary_10_1007_s11042_022_12407_z
crossref_primary_10_1002_cav_2011
crossref_primary_10_1016_j_neunet_2025_108010
crossref_primary_10_1109_JSEN_2023_3296167
crossref_primary_10_1007_s11063_024_11565_5
crossref_primary_10_1016_j_displa_2023_102550
crossref_primary_10_1109_LSP_2025_3597558
crossref_primary_10_1109_TCSVT_2024_3502801
crossref_primary_10_1016_j_cviu_2025_104491
crossref_primary_10_1117_1_JEI_32_4_043024
crossref_primary_10_1109_TMM_2022_3198327
crossref_primary_10_3390_math12193125
crossref_primary_10_1016_j_cviu_2025_104496
crossref_primary_10_7837_kosomes_2024_30_7_814
crossref_primary_10_1007_s00530_025_01708_6
crossref_primary_10_1109_TCE_2023_3280229
crossref_primary_10_1007_s11760_024_03021_7
crossref_primary_10_1109_TMM_2024_3400668
crossref_primary_10_1016_j_dsp_2023_104071
crossref_primary_10_1109_TMM_2022_3207330
crossref_primary_10_1145_3590965
crossref_primary_10_1109_TIM_2024_3370779
crossref_primary_10_3390_jimaging11080253
crossref_primary_10_1109_TIP_2023_3335822
crossref_primary_10_1109_ACCESS_2024_3408248
crossref_primary_10_3390_electronics14112220
crossref_primary_10_1016_j_displa_2025_103212
crossref_primary_10_1016_j_dsp_2025_105087
crossref_primary_10_1016_j_image_2022_116800
crossref_primary_10_1109_TPAMI_2025_3584921
crossref_primary_10_1038_s41598_024_81706_2
crossref_primary_10_1109_TIP_2025_3563775
crossref_primary_10_1016_j_jvcir_2022_103626
crossref_primary_10_1007_s10489_021_02627_5
crossref_primary_10_1016_j_displa_2025_103219
crossref_primary_10_1016_j_displa_2024_102863
crossref_primary_10_1109_TNNLS_2025_3561924
crossref_primary_10_1007_s00530_025_01750_4
crossref_primary_10_1016_j_eswa_2024_124301
crossref_primary_10_1109_TETCI_2023_3243920
crossref_primary_10_1088_1742_6596_1964_6_062046
crossref_primary_10_1109_TITS_2025_3526845
crossref_primary_10_1007_s00034_025_03017_9
crossref_primary_10_1016_j_displa_2025_103100
crossref_primary_10_1109_TCSVT_2022_3146731
crossref_primary_10_1016_j_patcog_2025_111628
crossref_primary_10_1109_TETCI_2023_3301337
crossref_primary_10_1109_TMM_2024_3521760
crossref_primary_10_1007_s11760_024_03239_5
crossref_primary_10_1016_j_compeleceng_2024_109750
crossref_primary_10_1016_j_engappai_2024_109521
crossref_primary_10_1016_j_asoc_2025_113546
crossref_primary_10_3390_photonics11080718
crossref_primary_10_1016_j_cviu_2025_104439
crossref_primary_10_1007_s11042_024_19128_5
crossref_primary_10_1109_TMM_2024_3413293
crossref_primary_10_1016_j_jvcir_2025_104480
crossref_primary_10_1109_TIM_2022_3232641
crossref_primary_10_1109_ACCESS_2024_3461859
crossref_primary_10_1109_TGRS_2024_3351134
crossref_primary_10_1109_TETCI_2024_3359051
crossref_primary_10_1109_TAI_2024_3499950
crossref_primary_10_1016_j_jvcir_2023_103932
crossref_primary_10_1109_TCSVT_2025_3547029
crossref_primary_10_1109_TNNLS_2023_3289626
crossref_primary_10_3390_s25051530
crossref_primary_10_1016_j_compeleceng_2024_109622
crossref_primary_10_1109_TMM_2022_3194993
crossref_primary_10_1109_TMM_2025_3543047
crossref_primary_10_1016_j_dsp_2025_105272
crossref_primary_10_1016_j_optlastec_2025_113686
crossref_primary_10_1007_s00371_022_02582_3
crossref_primary_10_1007_s10489_025_06771_0
crossref_primary_10_3390_photonics10030273
crossref_primary_10_1016_j_dsp_2024_104467
crossref_primary_10_1007_s00371_023_03249_3
crossref_primary_10_1016_j_knosys_2025_113827
crossref_primary_10_3390_electronics13183713
crossref_primary_10_1016_j_cag_2024_103921
crossref_primary_10_1007_s11554_024_01424_w
crossref_primary_10_1137_24M1680179
crossref_primary_10_1109_TIP_2025_3597046
crossref_primary_10_1631_FITEE_2200344
crossref_primary_10_1109_TIP_2025_3572788
crossref_primary_10_1016_j_neunet_2025_107764
crossref_primary_10_3390_s25175353
crossref_primary_10_1109_TIP_2025_3571339
crossref_primary_10_1109_TITS_2022_3165176
crossref_primary_10_3390_photonics11020190
crossref_primary_10_1016_j_ins_2023_119114
crossref_primary_10_3390_electronics12143162
crossref_primary_10_1007_s00371_025_03924_7
crossref_primary_10_1016_j_displa_2025_103136
crossref_primary_10_1016_j_dsp_2025_105044
crossref_primary_10_1016_j_cag_2025_104364
crossref_primary_10_1109_TCSVT_2023_3340506
crossref_primary_10_1109_LSP_2025_3563125
crossref_primary_10_1109_TMM_2024_3521752
crossref_primary_10_1016_j_cviu_2025_104466
crossref_primary_10_1117_1_JEI_34_1_013007
crossref_primary_10_1016_j_eswa_2025_128653
crossref_primary_10_1038_s41598_024_69505_1
crossref_primary_10_1016_j_knosys_2025_113382
crossref_primary_10_1109_TCSVT_2024_3426527
crossref_primary_10_3390_app15137382
crossref_primary_10_1109_TIP_2023_3266171
crossref_primary_10_1109_TPAMI_2025_3586712
crossref_primary_10_1109_LSP_2025_3556786
crossref_primary_10_1016_j_cviu_2024_103930
crossref_primary_10_1016_j_engappai_2023_106969
crossref_primary_10_1016_j_displa_2025_102979
crossref_primary_10_3390_electronics13183695
crossref_primary_10_1109_TITS_2024_3510832
crossref_primary_10_1016_j_displa_2025_103029
crossref_primary_10_1109_LSP_2024_3453120
crossref_primary_10_1109_TETCI_2024_3358200
crossref_primary_10_1007_s11042_023_15381_2
crossref_primary_10_1109_LSP_2025_3602001
crossref_primary_10_1007_s13042_023_02036_9
crossref_primary_10_1109_TNNLS_2025_3566647
crossref_primary_10_1016_j_engappai_2023_106611
crossref_primary_10_1109_ACCESS_2022_3197629
crossref_primary_10_1145_3638772
crossref_primary_10_1016_j_dsp_2024_104757
crossref_primary_10_1007_s10586_025_05494_8
crossref_primary_10_1007_s11263_024_02065_z
crossref_primary_10_1016_j_neucom_2025_130650
crossref_primary_10_1016_j_image_2023_116966
crossref_primary_10_1016_j_actaastro_2025_09_004
crossref_primary_10_1007_s11042_023_15851_7
crossref_primary_10_1016_j_patcog_2025_111814
crossref_primary_10_3390_app15010361
crossref_primary_10_1016_j_imavis_2024_105102
crossref_primary_10_1007_s12200_024_00129_z
crossref_primary_10_1016_j_image_2025_117264
crossref_primary_10_1016_j_neucom_2025_129426
crossref_primary_10_1109_JSEN_2025_3590815
crossref_primary_10_1016_j_imavis_2025_105645
crossref_primary_10_1145_3764933
crossref_primary_10_3390_s25165192
crossref_primary_10_1016_j_cag_2024_104089
crossref_primary_10_3390_s25154789
crossref_primary_10_1007_s10489_024_06044_2
crossref_primary_10_1016_j_knosys_2025_112998
crossref_primary_10_3390_app15105556
crossref_primary_10_1016_j_cag_2025_104182
crossref_primary_10_3390_app15031604
crossref_primary_10_1016_j_displa_2025_103040
crossref_primary_10_1016_j_neucom_2025_131052
crossref_primary_10_1109_TIP_2021_3068638
crossref_primary_10_1016_j_patcog_2024_110796
crossref_primary_10_1109_TMM_2022_3154152
crossref_primary_10_1016_j_neucom_2025_131174
crossref_primary_10_1016_j_cviu_2024_103952
crossref_primary_10_1007_s00530_025_01710_y
crossref_primary_10_32604_cmc_2025_059669
crossref_primary_10_1007_s00530_023_01252_1
crossref_primary_10_1016_j_engappai_2023_107234
crossref_primary_10_1016_j_inffus_2025_103380
crossref_primary_10_1016_j_patcog_2024_110799
crossref_primary_10_3390_computation9110117
crossref_primary_10_1016_j_displa_2025_103163
crossref_primary_10_1016_j_dsp_2025_105355
crossref_primary_10_1109_TPAMI_2025_3563612
crossref_primary_10_3390_app15168840
crossref_primary_10_1007_s11760_024_03804_y
crossref_primary_10_1109_TCSVT_2024_3454160
crossref_primary_10_1007_s10489_022_04013_1
crossref_primary_10_1109_LSP_2022_3163686
crossref_primary_10_1007_s11760_025_03885_3
crossref_primary_10_1016_j_patcog_2025_112371
crossref_primary_10_1109_ACCESS_2024_3513419
crossref_primary_10_1016_j_cag_2025_104170
crossref_primary_10_1016_j_cviu_2024_103948
crossref_primary_10_1016_j_knosys_2023_111099
crossref_primary_10_1016_j_neucom_2025_130196
crossref_primary_10_1109_TCI_2023_3240087
crossref_primary_10_1007_s11042_023_16650_w
crossref_primary_10_1016_j_engappai_2023_107003
crossref_primary_10_1016_j_jvcir_2024_104223
crossref_primary_10_1016_j_patcog_2023_110025
crossref_primary_10_1016_j_compeleceng_2024_109922
crossref_primary_10_1007_s11554_025_01690_2
crossref_primary_10_1109_JSEN_2024_3481416
crossref_primary_10_1016_j_dcan_2024_11_010
crossref_primary_10_1109_TNNLS_2024_3502424
crossref_primary_10_1117_1_JEI_32_2_023005
crossref_primary_10_3390_app14124962
crossref_primary_10_1007_s11760_025_04292_4
crossref_primary_10_3390_app15168850
crossref_primary_10_3390_s25185912
crossref_primary_10_1016_j_eswa_2025_129664
crossref_primary_10_1007_s11760_023_02673_1
crossref_primary_10_1016_j_cviu_2025_104428
crossref_primary_10_1109_TIP_2024_3519997
crossref_primary_10_1007_s00530_022_00913_x
crossref_primary_10_1016_j_eswa_2025_129782
crossref_primary_10_1016_j_patcog_2025_112360
crossref_primary_10_1016_j_sigpro_2025_110125
crossref_primary_10_1038_s41598_024_72912_z
Cites_doi 10.1109/CVPR.2018.00262
10.1109/TIP.2015.2442920
10.1145/2713168.2713194
10.1093/biomet/39.3-4.324
10.1109/ISPACS.2013.6704591
10.1109/CVPR.2019.00701
10.1145/3343031.3350926
10.1109/CVPR.2018.00347
10.1109/ICCV.2013.84
10.1109/TIP.2007.901238
10.1109/TIP.2013.2261309
10.1016/j.sigpro.2010.03.016
10.1109/TIP.2003.819861
10.1016/j.patcog.2016.06.008
10.1109/TIP.2013.2283400
10.1109/ISCAS.2018.8351427
10.1016/B978-0-12-336156-1.50061-6
10.1109/VBC.1990.109340
10.1109/TIP.2018.2794218
10.1109/ICPR.2016.7899725
10.1016/j.jvcir.2018.01.012
10.1109/TIP.2018.2810539
10.1109/CVPR.2016.304
10.1109/TCE.2007.4429280
10.1145/3072959.3073659
10.1109/TIP.2016.2598681
10.1109/TIP.2013.2284059
10.1145/2070781.2024208
10.1109/TIP.2017.2662206
10.1007/978-3-319-11752-2_43
10.1007/s00041-008-9045-x
10.1109/97.995823
10.1016/j.sigpro.2016.05.031
10.1145/1836845.1836920
10.1109/TCSVT.2017.2734838
10.1109/ICIP.2015.7351501
10.1109/TIP.2019.2958144
10.1109/TIP.2016.2639450
10.1109/TBC.2015.2459851
10.1109/ICCV.2015.123
10.1109/ICCVW.2017.356
10.1109/83.557356
10.1109/TIP.2019.2922106
10.1038/scientificamerican1277-108
10.1109/CVPR.2018.00577
10.1109/83.597272
10.1109/TCE.2007.381734
ContentType Journal Article
Copyright Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2021
Copyright_xml – notice: Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2021
DBID 97E
RIA
RIE
AAYXX
CITATION
NPM
7SC
7SP
8FD
JQ2
L7M
L~C
L~D
7X8
DOI 10.1109/TIP.2021.3050850
DatabaseName IEEE Xplore (IEEE)
IEEE All-Society Periodicals Package (ASPP) 1998–Present
IEEE Electronic Library (IEL)
CrossRef
PubMed
Computer and Information Systems Abstracts
Electronics & Communications Abstracts
Technology Research Database
ProQuest Computer Science Collection
Advanced Technologies Database with Aerospace
Computer and Information Systems Abstracts – Academic
Computer and Information Systems Abstracts Professional
MEDLINE - Academic
DatabaseTitle CrossRef
PubMed
Technology Research Database
Computer and Information Systems Abstracts – Academic
Electronics & Communications Abstracts
ProQuest Computer Science Collection
Computer and Information Systems Abstracts
Advanced Technologies Database with Aerospace
Computer and Information Systems Abstracts Professional
MEDLINE - Academic
DatabaseTitleList MEDLINE - Academic
Technology Research Database
PubMed

Database_xml – sequence: 1
  dbid: NPM
  name: PubMed
  url: http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed
  sourceTypes: Index Database
– sequence: 2
  dbid: RIE
  name: IEEE Electronic Library (IEL)
  url: https://ieeexplore.ieee.org/
  sourceTypes: Publisher
– sequence: 3
  dbid: 7X8
  name: MEDLINE - Academic
  url: https://search.proquest.com/medline
  sourceTypes: Aggregation Database
DeliveryMethod fulltext_linktorsrc
Discipline Applied Sciences
Engineering
EISSN 1941-0042
EndPage 1
ExternalDocumentID 33460379
10_1109_TIP_2021_3050850
9328179
Genre orig-research
Journal Article
GroupedDBID ---
-~X
.DC
0R~
29I
4.4
5GY
6IK
97E
AAJGR
AARMG
AASAJ
AAWTH
ABAZT
ABQJQ
ABVLG
ACGFO
ACGFS
ACIWK
AENEX
AGQYO
AHBIQ
AKJIK
AKQYR
ALMA_UNASSIGNED_HOLDINGS
ASUFR
ATWAV
BEFXN
BFFAM
BGNUA
BKEBE
BPEOZ
CS3
DU5
EBS
F5P
HZ~
IFIPE
IPLJI
JAVBF
LAI
M43
MS~
O9-
OCL
P2P
RIA
RIE
RNS
TAE
TN5
53G
5VS
AAYXX
ABFSI
AETIX
AGSQL
AI.
AIBXA
ALLEH
CITATION
E.L
EJD
H~9
ICLAB
IFJZH
VH1
AAYOK
NPM
PKN
RIG
Z5M
7SC
7SP
8FD
JQ2
L7M
L~C
L~D
7X8
ID FETCH-LOGICAL-c347t-dcad442924492b44a6024b46ca7b46cab914bba9218f482e8e02b64902e7e4303
IEDL.DBID RIE
ISICitedReferencesCount 422
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000612145300006&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 1057-7149
1941-0042
IngestDate Thu Oct 02 13:44:18 EDT 2025
Mon Jun 30 10:18:07 EDT 2025
Wed Feb 19 02:29:15 EST 2025
Sat Nov 29 03:21:14 EST 2025
Tue Nov 18 22:35:39 EST 2025
Wed Aug 27 06:01:51 EDT 2025
IsPeerReviewed true
IsScholarly true
Language English
License https://ieeexplore.ieee.org/Xplorehelp/downloads/license-information/IEEE.html
https://doi.org/10.15223/policy-029
https://doi.org/10.15223/policy-037
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-c347t-dcad442924492b44a6024b46ca7b46cab914bba9218f482e8e02b64902e7e4303
Notes ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
content type line 23
ORCID 0000-0002-3583-959X
0000-0002-1692-0069
0000-0002-0468-9576
0000-0003-3951-3877
PMID 33460379
PQID 2480864498
PQPubID 85429
PageCount 1
ParticipantIDs crossref_citationtrail_10_1109_TIP_2021_3050850
pubmed_primary_33460379
proquest_miscellaneous_2479042373
proquest_journals_2480864498
crossref_primary_10_1109_TIP_2021_3050850
ieee_primary_9328179
PublicationCentury 2000
PublicationDate 2021-01-01
PublicationDateYYYYMMDD 2021-01-01
PublicationDate_xml – month: 01
  year: 2021
  text: 2021-01-01
  day: 01
PublicationDecade 2020
PublicationPlace United States
PublicationPlace_xml – name: United States
– name: New York
PublicationTitle IEEE transactions on image processing
PublicationTitleAbbrev TIP
PublicationTitleAlternate IEEE Trans Image Process
PublicationYear 2021
Publisher IEEE
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Publisher_xml – name: IEEE
– name: The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
References ref57
ref13
ref56
ref12
ref15
ref58
ref14
xu (ref30) 2014
ref52
ref55
ref11
ref54
ref10
ref17
ref16
gwn lore (ref53) 2015
zhang (ref22) 2012
gatys (ref31) 2015
ref50
ref45
ref48
ying (ref51) 2017
ref47
ref42
ref41
ref44
ying (ref46) 2017
ref43
köhler (ref27) 2014
ref49
ref8
ref7
ref9
ref4
ref3
ref6
ref5
li (ref59) 2014
ref40
ref35
ref37
ref36
zhang (ref34) 2016
ref33
ref32
chen (ref20) 2018
ref2
ref1
ref39
schuler (ref29) 2014
ref24
ref23
xu (ref38) 2011; 30
ref26
ref25
shen (ref19) 2017
ref21
liang (ref18) 2020
ref28
jiang (ref60) 2019
ref61
References_xml – year: 2020
  ident: ref18
  article-title: Deep bilateral retinex for low-light image enhancement
  publication-title: arXiv 2007 02018
– year: 2017
  ident: ref19
  article-title: MSR-net:Low-light image enhancement using deep convolutional network
  publication-title: arXiv 1711 02488
– ident: ref37
  doi: 10.1109/CVPR.2018.00262
– ident: ref42
  doi: 10.1109/TIP.2015.2442920
– ident: ref45
  doi: 10.1145/2713168.2713194
– start-page: 36
  year: 2017
  ident: ref51
  article-title: A new image contrast enhancement algorithm using exposure fusion framework
  publication-title: Int Conf Comput Anal Image Patterns
– ident: ref61
  doi: 10.1093/biomet/39.3-4.324
– ident: ref49
  doi: 10.1109/ISPACS.2013.6704591
– year: 2015
  ident: ref53
  article-title: LLNet: A deep autoencoder approach to natural low-light image enhancement
  publication-title: arXiv 1511 03995
– ident: ref15
  doi: 10.1109/CVPR.2019.00701
– ident: ref17
  doi: 10.1145/3343031.3350926
– year: 2014
  ident: ref29
  article-title: Learning to deblur
  publication-title: arXiv 1406 7444
– ident: ref13
  doi: 10.1109/CVPR.2018.00347
– ident: ref33
  doi: 10.1109/ICCV.2013.84
– ident: ref23
  doi: 10.1109/TIP.2007.901238
– year: 2017
  ident: ref46
  article-title: A bio-inspired multi-exposure fusion framework for low-light image enhancement
  publication-title: arXiv 1711 00591
– start-page: 1
  year: 2018
  ident: ref20
  article-title: Deep Retinex decomposition for low-light enhancement
  publication-title: Proc Brit Mach Vis Conf
– ident: ref6
  doi: 10.1109/TIP.2013.2261309
– ident: ref44
  doi: 10.1016/j.sigpro.2010.03.016
– ident: ref55
  doi: 10.1109/TIP.2003.819861
– ident: ref14
  doi: 10.1016/j.patcog.2016.06.008
– year: 2019
  ident: ref60
  article-title: EnlightenGAN: Deep light enhancement without paired supervision
  publication-title: arXiv 1906 06972
– year: 2015
  ident: ref31
  article-title: A neural algorithm of artistic style
  publication-title: arXiv 1508 06576
– ident: ref58
  doi: 10.1109/TIP.2013.2283400
– ident: ref11
  doi: 10.1109/ISCAS.2018.8351427
– ident: ref52
  doi: 10.1016/B978-0-12-336156-1.50061-6
– ident: ref1
  doi: 10.1109/VBC.1990.109340
– ident: ref16
  doi: 10.1109/TIP.2018.2794218
– ident: ref36
  doi: 10.1109/ICPR.2016.7899725
– ident: ref41
  doi: 10.1016/j.jvcir.2018.01.012
– ident: ref10
  doi: 10.1109/TIP.2018.2810539
– start-page: 1790
  year: 2014
  ident: ref30
  article-title: Deep convolutional neural network for image deconvolution
  publication-title: Proc Annu Conf Neural Inf Process Syst
– ident: ref9
  doi: 10.1109/CVPR.2016.304
– start-page: 2034
  year: 2012
  ident: ref22
  article-title: Enhancement and noise reduction of very low light level images
  publication-title: Proc IEEE Int Conf Pattern Recognit
– ident: ref47
  doi: 10.1109/TCE.2007.4429280
– ident: ref26
  doi: 10.1145/3072959.3073659
– ident: ref32
  doi: 10.1109/TIP.2016.2598681
– ident: ref43
  doi: 10.1109/TIP.2013.2284059
– volume: 30
  start-page: 174:1
  year: 2011
  ident: ref38
  article-title: Image smoothing via L0 gradient minimization
  publication-title: ACM Trans Graph
  doi: 10.1145/2070781.2024208
– ident: ref25
  doi: 10.1109/TIP.2017.2662206
– start-page: 523
  year: 2014
  ident: ref27
  article-title: Mask-specific inpainting with deep neural networks
  publication-title: Proc Pattern Recognit
  doi: 10.1007/978-3-319-11752-2_43
– ident: ref39
  doi: 10.1007/s00041-008-9045-x
– ident: ref56
  doi: 10.1109/97.995823
– ident: ref7
  doi: 10.1016/j.sigpro.2016.05.031
– ident: ref50
  doi: 10.1145/1836845.1836920
– ident: ref35
  doi: 10.1109/TCSVT.2017.2734838
– ident: ref21
  doi: 10.1109/ICIP.2015.7351501
– start-page: 174
  year: 2014
  ident: ref59
  article-title: A contrast enhancement framework with jpeg artifacts suppression
  publication-title: Proc IEEE Conf Computer Communications
– ident: ref24
  doi: 10.1109/TIP.2019.2958144
– ident: ref8
  doi: 10.1109/TIP.2016.2639450
– ident: ref57
  doi: 10.1109/TBC.2015.2459851
– ident: ref54
  doi: 10.1109/ICCV.2015.123
– ident: ref48
  doi: 10.1109/ICCVW.2017.356
– ident: ref40
  doi: 10.1109/TIP.2003.819861
– year: 2016
  ident: ref34
  article-title: Beyond a Gaussian denoiser: Residual learning of deep CNN for image denoising
  publication-title: arXiv 1608 03981
– ident: ref4
  doi: 10.1109/83.557356
– ident: ref12
  doi: 10.1109/TIP.2019.2922106
– ident: ref3
  doi: 10.1038/scientificamerican1277-108
– ident: ref28
  doi: 10.1109/CVPR.2018.00577
– ident: ref5
  doi: 10.1109/83.597272
– ident: ref2
  doi: 10.1109/TCE.2007.381734
SSID ssj0014516
Score 2.726556
Snippet Due to the absence of a desirable objective for low-light image enhancement, previous data-driven methods may provide undesirable enhanced results including...
SourceID proquest
pubmed
crossref
ieee
SourceType Aggregation Database
Index Database
Enrichment Source
Publisher
StartPage 1
SubjectTerms Atmospheric modeling
denoising
Illumination
Image coding
Image compression
Image enhancement
Image restoration
Light
Lighting
Low-light enhancement
Minimization
Noise
Noise reduction
Reflectance
Regularization
residual dense network
Retinex model
sparse gradient regularization
Title Sparse Gradient Regularized Deep Retinex Network for Robust Low-Light Image Enhancement
URI https://ieeexplore.ieee.org/document/9328179
https://www.ncbi.nlm.nih.gov/pubmed/33460379
https://www.proquest.com/docview/2480864498
https://www.proquest.com/docview/2479042373
Volume 30
WOSCitedRecordID wos000612145300006&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
journalDatabaseRights – providerCode: PRVIEE
  databaseName: IEEE Electronic Library (IEL)
  customDbUrl:
  eissn: 1941-0042
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0014516
  issn: 1057-7149
  databaseCode: RIE
  dateStart: 19920101
  isFulltext: true
  titleUrlDefault: https://ieeexplore.ieee.org/
  providerName: IEEE
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1LT9wwEB4B6qE9AIUWwkuu1Eulhs3Die0j4tEirVaIR7u3KI5nBRIkq90sIH49YycbgQSVeomiZJw4-caeGc94BuA71zrUQTLyIzJofZ7TPKhNGPqJ0sYWStKJ2_X-py8GAzkcqrMF-NnthUFEF3yG-_bU-fJNVczsUlmPdA1JDLQIi0KIZq9W5zGwBWedZzMRviC1f-6SDFTv8vSMDMEo3CfethnaXokgV1PlffXSiZmTlf_r4Cost-okO2jw_wwLWK7BSqtasnbgTtfg04u8g-vw92JM9iyyXxMX8FWzc1eRfnLzRI2OEMd0oSbyRzZoosQZqbbsvNKzac361YPftyY9O72jyYgdl9eWc2zPvsDVyfHl4W-_rbDgFzEXtW-K3HBbsIpzFWnO85REtuZpkQt31CokMHNFesCIywglBpFOuQoiFMhJ-n2FpbIqcRNYIUkTIntISROSwIuVFolBTBVybrQ2HvTmPz0r2vTjtgrGbebMkEBlBFNmYcpamDz40bUYN6k3_kG7btHo6FogPNiZ45q1Y3OaRVySHUdfLD341t2mUWVdJXmJ1czSCOUihmIPNhp-6J4dxzwNYqG23n7nNny0PWuWaXZgqZ7McBc-FPf1zXSyR6w7lHuOdZ8BkEXn1w
linkProvider IEEE
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV3db9QwDLfGmAQ8MNj4KGyQSXuZRHf9cJvmEcE-TpTTtB1jb1XTeGIStKe7HiD-epy0V4EESLxUVeu0ae3EP8eODbCPWoc6SK79iA1aH0ueB7UJQz9R2thCSTpxu94vczmZZFdX6mwNXg17YYjIBZ_RoT11vnzTVEu7VDZirJGxAN2C2wliFHa7tQafgS0563ybifQlA_-VUzJQo-n4jE3BKDxk6bY52n5TQq6qyt8BplM0x5v_18UHcL8HlOJ1JwEPYY3qLdjswaXoh-5iC-79knlwGz5ezNiiJXEydyFfrTh3NennNz-40VuiGV9omfy7mHRx4oLBrThv9HLRirz55ufWqBfjLzwdiaP6k5Ud27NH8OH4aPrm1O9rLPhVjLL1TVUatCWrEFWkEcuUlbbGtCqlO2oVMjtLxUjgGrOIMgoinaIKIpKErP8ew3rd1PQURJUxFmKLSGUmZJUXKy0TQ5QqQjRaGw9Gq59eVH0CclsH43PhDJFAFcymwrKp6NnkwcHQYtYl3_gH7bblxkDXM8KDnRVfi350LooIM7bk-IszD_aG2zyurLOkrKlZWhqpXMxQ7MGTTh6GZ8cxpkEs1bM_v_Ml3Dmdvs-LfDx59xzu2l52izY7sN7Ol7QLG9XX9mYxf-EE-CdOIOo2
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%3Ajournal&rft.genre=article&rft.atitle=Sparse+Gradient+Regularized+Deep+Retinex+Network+for+Robust+Low-Light+Image+Enhancement&rft.jtitle=IEEE+transactions+on+image+processing&rft.au=Yang%2C+Wenhan&rft.au=Wang%2C+Wenjing&rft.au=Huang%2C+Haofeng&rft.au=Wang%2C+Shiqi&rft.date=2021-01-01&rft.issn=1057-7149&rft.eissn=1941-0042&rft.volume=30&rft.spage=2072&rft.epage=2086&rft_id=info:doi/10.1109%2FTIP.2021.3050850&rft.externalDBID=n%2Fa&rft.externalDocID=10_1109_TIP_2021_3050850
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1057-7149&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1057-7149&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1057-7149&client=summon