Attention-Guided Multi-Scale Feature Fusion Network for Low-Light Image Enhancement

Low-light image enhancement has been an important research branch in the field of computer vision. Low-light images are characterized by poor visibility, high noise and low contrast. To improve low-light images generated in low-light environments and night conditions, we propose an Attention-Guided...
Ausführliche Beschreibung

Gespeichert in:

Autor*in:	HengShuai Cui [verfasserIn] Jinjiang Li [verfasserIn] Zhen Hua [verfasserIn] Linwei Fan [verfasserIn]

Format:	E-Artikel
Sprache:	Englisch

Erschienen:	2022

Schlagwörter:	low-light image enhancement multi-scale attention mechanism feature calibration cascade fusion coarse-to-fine

Übergeordnetes Werk:	In: Frontiers in Neurorobotics - Frontiers Media S.A., 2008, 16(2022)
Übergeordnetes Werk:	volume:16 ; year:2022

Links:	Link aufrufen Link aufrufen Link aufrufen Journal toc

DOI / URN:	10.3389/fnbot.2022.837208

Katalog-ID:	DOAJ018075266

Internformat


LEADER	01000caa a22002652 4500
001	DOAJ018075266
003	DE-627
005	20230310094327.0
007	cr uuu---uuuuu
008	230226s2022 xx \|\|\|\|\|o 00\| \|\|eng c
024	7		\|a 10.3389/fnbot.2022.837208 \|2 doi
035			\|a (DE-627)DOAJ018075266
035			\|a (DE-599)DOAJ19e5af8ada204f8db7352799ee30edba
040			\|a DE-627 \|b ger \|c DE-627 \|e rakwb
041			\|a eng
050		0	\|a RC321-571
100	0		\|a HengShuai Cui \|e verfasserin \|4 aut
245	1	0	\|a Attention-Guided Multi-Scale Feature Fusion Network for Low-Light Image Enhancement
264		1	\|c 2022
336			\|a Text \|b txt \|2 rdacontent
337			\|a Computermedien \|b c \|2 rdamedia
338			\|a Online-Ressource \|b cr \|2 rdacarrier
520			\|a Low-light image enhancement has been an important research branch in the field of computer vision. Low-light images are characterized by poor visibility, high noise and low contrast. To improve low-light images generated in low-light environments and night conditions, we propose an Attention-Guided Multi-scale feature fusion network (MSFFNet) for low-light image enhancement for enhancing the contrast and brightness of low-light images. First, to avoid the high cost computation arising from the stacking of multiple sub-networks, our network uses a single encoder and decoder for multi-scale input and output images. Multi-scale input images can make up for the lack of pixel information and loss of feature map information caused by a single input image. The multi-scale output image can effectively monitor the error loss in the image reconstruction process. Second, the Convolutional Block Attention Module (CBAM) is introduced in the encoder part to effectively suppress the noise and color difference generated during feature extraction and further guide the network to refine the color features. Feature calibration module (FCM) is introduced in the decoder section to enhance the mapping expression between channels. Attention fusion module (AFM) is also added to capture contextual information, which is more conducive to recovering image detail information. Last, the cascade fusion module (CFM) is introduced to effectively combine the feature map information under different perceptual fields. Sufficient qualitative and quantitative experiments have been conducted on a variety of publicly available datasets, and the proposed MSFFNet outperforms other low-light enhancement methods in terms of visual effects and metric scores.
650		4	\|a low-light image enhancement
650		4	\|a multi-scale
650		4	\|a attention mechanism
650		4	\|a feature calibration
650		4	\|a cascade fusion
650		4	\|a coarse-to-fine
653		0	\|a Neurosciences. Biological psychiatry. Neuropsychiatry
700	0		\|a Jinjiang Li \|e verfasserin \|4 aut
700	0		\|a Jinjiang Li \|e verfasserin \|4 aut
700	0		\|a Zhen Hua \|e verfasserin \|4 aut
700	0		\|a Zhen Hua \|e verfasserin \|4 aut
700	0		\|a Linwei Fan \|e verfasserin \|4 aut
773	0	8	\|i In \|t Frontiers in Neurorobotics \|d Frontiers Media S.A., 2008 \|g 16(2022) \|w (DE-627)579826716 \|w (DE-600)2453002-5 \|x 16625218 \|7 nnns
773	1	8	\|g volume:16 \|g year:2022
856	4	0	\|u https://doi.org/10.3389/fnbot.2022.837208 \|z kostenfrei
856	4	0	\|u https://doaj.org/article/19e5af8ada204f8db7352799ee30edba \|z kostenfrei
856	4	0	\|u https://www.frontiersin.org/articles/10.3389/fnbot.2022.837208/full \|z kostenfrei
856	4	2	\|u https://doaj.org/toc/1662-5218 \|y Journal toc \|z kostenfrei
912			\|a GBV_USEFLAG_A
912			\|a SYSFLAG_A
912			\|a GBV_DOAJ
912			\|a GBV_ILN_11
912			\|a GBV_ILN_20
912			\|a GBV_ILN_22
912			\|a GBV_ILN_23
912			\|a GBV_ILN_24
912			\|a GBV_ILN_39
912			\|a GBV_ILN_40
912			\|a GBV_ILN_60
912			\|a GBV_ILN_62
912			\|a GBV_ILN_63
912			\|a GBV_ILN_65
912			\|a GBV_ILN_69
912			\|a GBV_ILN_70
912			\|a GBV_ILN_73
912			\|a GBV_ILN_74
912			\|a GBV_ILN_95
912			\|a GBV_ILN_105
912			\|a GBV_ILN_110
912			\|a GBV_ILN_151
912			\|a GBV_ILN_161
912			\|a GBV_ILN_170
912			\|a GBV_ILN_206
912			\|a GBV_ILN_213
912			\|a GBV_ILN_230
912			\|a GBV_ILN_285
912			\|a GBV_ILN_293
912			\|a GBV_ILN_370
912			\|a GBV_ILN_602
912			\|a GBV_ILN_2003
912			\|a GBV_ILN_2014
912			\|a GBV_ILN_2055
912			\|a GBV_ILN_4012
912			\|a GBV_ILN_4037
912			\|a GBV_ILN_4112
912			\|a GBV_ILN_4125
912			\|a GBV_ILN_4126
912			\|a GBV_ILN_4249
912			\|a GBV_ILN_4305
912			\|a GBV_ILN_4306
912			\|a GBV_ILN_4307
912			\|a GBV_ILN_4313
912			\|a GBV_ILN_4322
912			\|a GBV_ILN_4323
912			\|a GBV_ILN_4324
912			\|a GBV_ILN_4325
912			\|a GBV_ILN_4335
912			\|a GBV_ILN_4338
912			\|a GBV_ILN_4367
912			\|a GBV_ILN_4700
951			\|a AR
952			\|d 16 \|j 2022

Indexfelder

author_variant	h c hc j l jl j l jl z h zh z h zh l f lf
matchkey_str	article:16625218:2022----::tetogiemliclfaueuinewrfrolg
hierarchy_sort_str	2022
callnumber-subject-code	RC
publishDate	2022
allfields	10.3389/fnbot.2022.837208 doi (DE-627)DOAJ018075266 (DE-599)DOAJ19e5af8ada204f8db7352799ee30edba DE-627 ger DE-627 rakwb eng RC321-571 HengShuai Cui verfasserin aut Attention-Guided Multi-Scale Feature Fusion Network for Low-Light Image Enhancement 2022 Text txt rdacontent Computermedien c rdamedia Online-Ressource cr rdacarrier Low-light image enhancement has been an important research branch in the field of computer vision. Low-light images are characterized by poor visibility, high noise and low contrast. To improve low-light images generated in low-light environments and night conditions, we propose an Attention-Guided Multi-scale feature fusion network (MSFFNet) for low-light image enhancement for enhancing the contrast and brightness of low-light images. First, to avoid the high cost computation arising from the stacking of multiple sub-networks, our network uses a single encoder and decoder for multi-scale input and output images. Multi-scale input images can make up for the lack of pixel information and loss of feature map information caused by a single input image. The multi-scale output image can effectively monitor the error loss in the image reconstruction process. Second, the Convolutional Block Attention Module (CBAM) is introduced in the encoder part to effectively suppress the noise and color difference generated during feature extraction and further guide the network to refine the color features. Feature calibration module (FCM) is introduced in the decoder section to enhance the mapping expression between channels. Attention fusion module (AFM) is also added to capture contextual information, which is more conducive to recovering image detail information. Last, the cascade fusion module (CFM) is introduced to effectively combine the feature map information under different perceptual fields. Sufficient qualitative and quantitative experiments have been conducted on a variety of publicly available datasets, and the proposed MSFFNet outperforms other low-light enhancement methods in terms of visual effects and metric scores. low-light image enhancement multi-scale attention mechanism feature calibration cascade fusion coarse-to-fine Neurosciences. Biological psychiatry. Neuropsychiatry Jinjiang Li verfasserin aut Jinjiang Li verfasserin aut Zhen Hua verfasserin aut Zhen Hua verfasserin aut Linwei Fan verfasserin aut In Frontiers in Neurorobotics Frontiers Media S.A., 2008 16(2022) (DE-627)579826716 (DE-600)2453002-5 16625218 nnns volume:16 year:2022 https://doi.org/10.3389/fnbot.2022.837208 kostenfrei https://doaj.org/article/19e5af8ada204f8db7352799ee30edba kostenfrei https://www.frontiersin.org/articles/10.3389/fnbot.2022.837208/full kostenfrei https://doaj.org/toc/1662-5218 Journal toc kostenfrei GBV_USEFLAG_A SYSFLAG_A GBV_DOAJ GBV_ILN_11 GBV_ILN_20 GBV_ILN_22 GBV_ILN_23 GBV_ILN_24 GBV_ILN_39 GBV_ILN_40 GBV_ILN_60 GBV_ILN_62 GBV_ILN_63 GBV_ILN_65 GBV_ILN_69 GBV_ILN_70 GBV_ILN_73 GBV_ILN_74 GBV_ILN_95 GBV_ILN_105 GBV_ILN_110 GBV_ILN_151 GBV_ILN_161 GBV_ILN_170 GBV_ILN_206 GBV_ILN_213 GBV_ILN_230 GBV_ILN_285 GBV_ILN_293 GBV_ILN_370 GBV_ILN_602 GBV_ILN_2003 GBV_ILN_2014 GBV_ILN_2055 GBV_ILN_4012 GBV_ILN_4037 GBV_ILN_4112 GBV_ILN_4125 GBV_ILN_4126 GBV_ILN_4249 GBV_ILN_4305 GBV_ILN_4306 GBV_ILN_4307 GBV_ILN_4313 GBV_ILN_4322 GBV_ILN_4323 GBV_ILN_4324 GBV_ILN_4325 GBV_ILN_4335 GBV_ILN_4338 GBV_ILN_4367 GBV_ILN_4700 AR 16 2022
spelling	10.3389/fnbot.2022.837208 doi (DE-627)DOAJ018075266 (DE-599)DOAJ19e5af8ada204f8db7352799ee30edba DE-627 ger DE-627 rakwb eng RC321-571 HengShuai Cui verfasserin aut Attention-Guided Multi-Scale Feature Fusion Network for Low-Light Image Enhancement 2022 Text txt rdacontent Computermedien c rdamedia Online-Ressource cr rdacarrier Low-light image enhancement has been an important research branch in the field of computer vision. Low-light images are characterized by poor visibility, high noise and low contrast. To improve low-light images generated in low-light environments and night conditions, we propose an Attention-Guided Multi-scale feature fusion network (MSFFNet) for low-light image enhancement for enhancing the contrast and brightness of low-light images. First, to avoid the high cost computation arising from the stacking of multiple sub-networks, our network uses a single encoder and decoder for multi-scale input and output images. Multi-scale input images can make up for the lack of pixel information and loss of feature map information caused by a single input image. The multi-scale output image can effectively monitor the error loss in the image reconstruction process. Second, the Convolutional Block Attention Module (CBAM) is introduced in the encoder part to effectively suppress the noise and color difference generated during feature extraction and further guide the network to refine the color features. Feature calibration module (FCM) is introduced in the decoder section to enhance the mapping expression between channels. Attention fusion module (AFM) is also added to capture contextual information, which is more conducive to recovering image detail information. Last, the cascade fusion module (CFM) is introduced to effectively combine the feature map information under different perceptual fields. Sufficient qualitative and quantitative experiments have been conducted on a variety of publicly available datasets, and the proposed MSFFNet outperforms other low-light enhancement methods in terms of visual effects and metric scores. low-light image enhancement multi-scale attention mechanism feature calibration cascade fusion coarse-to-fine Neurosciences. Biological psychiatry. Neuropsychiatry Jinjiang Li verfasserin aut Jinjiang Li verfasserin aut Zhen Hua verfasserin aut Zhen Hua verfasserin aut Linwei Fan verfasserin aut In Frontiers in Neurorobotics Frontiers Media S.A., 2008 16(2022) (DE-627)579826716 (DE-600)2453002-5 16625218 nnns volume:16 year:2022 https://doi.org/10.3389/fnbot.2022.837208 kostenfrei https://doaj.org/article/19e5af8ada204f8db7352799ee30edba kostenfrei https://www.frontiersin.org/articles/10.3389/fnbot.2022.837208/full kostenfrei https://doaj.org/toc/1662-5218 Journal toc kostenfrei GBV_USEFLAG_A SYSFLAG_A GBV_DOAJ GBV_ILN_11 GBV_ILN_20 GBV_ILN_22 GBV_ILN_23 GBV_ILN_24 GBV_ILN_39 GBV_ILN_40 GBV_ILN_60 GBV_ILN_62 GBV_ILN_63 GBV_ILN_65 GBV_ILN_69 GBV_ILN_70 GBV_ILN_73 GBV_ILN_74 GBV_ILN_95 GBV_ILN_105 GBV_ILN_110 GBV_ILN_151 GBV_ILN_161 GBV_ILN_170 GBV_ILN_206 GBV_ILN_213 GBV_ILN_230 GBV_ILN_285 GBV_ILN_293 GBV_ILN_370 GBV_ILN_602 GBV_ILN_2003 GBV_ILN_2014 GBV_ILN_2055 GBV_ILN_4012 GBV_ILN_4037 GBV_ILN_4112 GBV_ILN_4125 GBV_ILN_4126 GBV_ILN_4249 GBV_ILN_4305 GBV_ILN_4306 GBV_ILN_4307 GBV_ILN_4313 GBV_ILN_4322 GBV_ILN_4323 GBV_ILN_4324 GBV_ILN_4325 GBV_ILN_4335 GBV_ILN_4338 GBV_ILN_4367 GBV_ILN_4700 AR 16 2022
allfields_unstemmed	10.3389/fnbot.2022.837208 doi (DE-627)DOAJ018075266 (DE-599)DOAJ19e5af8ada204f8db7352799ee30edba DE-627 ger DE-627 rakwb eng RC321-571 HengShuai Cui verfasserin aut Attention-Guided Multi-Scale Feature Fusion Network for Low-Light Image Enhancement 2022 Text txt rdacontent Computermedien c rdamedia Online-Ressource cr rdacarrier Low-light image enhancement has been an important research branch in the field of computer vision. Low-light images are characterized by poor visibility, high noise and low contrast. To improve low-light images generated in low-light environments and night conditions, we propose an Attention-Guided Multi-scale feature fusion network (MSFFNet) for low-light image enhancement for enhancing the contrast and brightness of low-light images. First, to avoid the high cost computation arising from the stacking of multiple sub-networks, our network uses a single encoder and decoder for multi-scale input and output images. Multi-scale input images can make up for the lack of pixel information and loss of feature map information caused by a single input image. The multi-scale output image can effectively monitor the error loss in the image reconstruction process. Second, the Convolutional Block Attention Module (CBAM) is introduced in the encoder part to effectively suppress the noise and color difference generated during feature extraction and further guide the network to refine the color features. Feature calibration module (FCM) is introduced in the decoder section to enhance the mapping expression between channels. Attention fusion module (AFM) is also added to capture contextual information, which is more conducive to recovering image detail information. Last, the cascade fusion module (CFM) is introduced to effectively combine the feature map information under different perceptual fields. Sufficient qualitative and quantitative experiments have been conducted on a variety of publicly available datasets, and the proposed MSFFNet outperforms other low-light enhancement methods in terms of visual effects and metric scores. low-light image enhancement multi-scale attention mechanism feature calibration cascade fusion coarse-to-fine Neurosciences. Biological psychiatry. Neuropsychiatry Jinjiang Li verfasserin aut Jinjiang Li verfasserin aut Zhen Hua verfasserin aut Zhen Hua verfasserin aut Linwei Fan verfasserin aut In Frontiers in Neurorobotics Frontiers Media S.A., 2008 16(2022) (DE-627)579826716 (DE-600)2453002-5 16625218 nnns volume:16 year:2022 https://doi.org/10.3389/fnbot.2022.837208 kostenfrei https://doaj.org/article/19e5af8ada204f8db7352799ee30edba kostenfrei https://www.frontiersin.org/articles/10.3389/fnbot.2022.837208/full kostenfrei https://doaj.org/toc/1662-5218 Journal toc kostenfrei GBV_USEFLAG_A SYSFLAG_A GBV_DOAJ GBV_ILN_11 GBV_ILN_20 GBV_ILN_22 GBV_ILN_23 GBV_ILN_24 GBV_ILN_39 GBV_ILN_40 GBV_ILN_60 GBV_ILN_62 GBV_ILN_63 GBV_ILN_65 GBV_ILN_69 GBV_ILN_70 GBV_ILN_73 GBV_ILN_74 GBV_ILN_95 GBV_ILN_105 GBV_ILN_110 GBV_ILN_151 GBV_ILN_161 GBV_ILN_170 GBV_ILN_206 GBV_ILN_213 GBV_ILN_230 GBV_ILN_285 GBV_ILN_293 GBV_ILN_370 GBV_ILN_602 GBV_ILN_2003 GBV_ILN_2014 GBV_ILN_2055 GBV_ILN_4012 GBV_ILN_4037 GBV_ILN_4112 GBV_ILN_4125 GBV_ILN_4126 GBV_ILN_4249 GBV_ILN_4305 GBV_ILN_4306 GBV_ILN_4307 GBV_ILN_4313 GBV_ILN_4322 GBV_ILN_4323 GBV_ILN_4324 GBV_ILN_4325 GBV_ILN_4335 GBV_ILN_4338 GBV_ILN_4367 GBV_ILN_4700 AR 16 2022
allfieldsGer	10.3389/fnbot.2022.837208 doi (DE-627)DOAJ018075266 (DE-599)DOAJ19e5af8ada204f8db7352799ee30edba DE-627 ger DE-627 rakwb eng RC321-571 HengShuai Cui verfasserin aut Attention-Guided Multi-Scale Feature Fusion Network for Low-Light Image Enhancement 2022 Text txt rdacontent Computermedien c rdamedia Online-Ressource cr rdacarrier Low-light image enhancement has been an important research branch in the field of computer vision. Low-light images are characterized by poor visibility, high noise and low contrast. To improve low-light images generated in low-light environments and night conditions, we propose an Attention-Guided Multi-scale feature fusion network (MSFFNet) for low-light image enhancement for enhancing the contrast and brightness of low-light images. First, to avoid the high cost computation arising from the stacking of multiple sub-networks, our network uses a single encoder and decoder for multi-scale input and output images. Multi-scale input images can make up for the lack of pixel information and loss of feature map information caused by a single input image. The multi-scale output image can effectively monitor the error loss in the image reconstruction process. Second, the Convolutional Block Attention Module (CBAM) is introduced in the encoder part to effectively suppress the noise and color difference generated during feature extraction and further guide the network to refine the color features. Feature calibration module (FCM) is introduced in the decoder section to enhance the mapping expression between channels. Attention fusion module (AFM) is also added to capture contextual information, which is more conducive to recovering image detail information. Last, the cascade fusion module (CFM) is introduced to effectively combine the feature map information under different perceptual fields. Sufficient qualitative and quantitative experiments have been conducted on a variety of publicly available datasets, and the proposed MSFFNet outperforms other low-light enhancement methods in terms of visual effects and metric scores. low-light image enhancement multi-scale attention mechanism feature calibration cascade fusion coarse-to-fine Neurosciences. Biological psychiatry. Neuropsychiatry Jinjiang Li verfasserin aut Jinjiang Li verfasserin aut Zhen Hua verfasserin aut Zhen Hua verfasserin aut Linwei Fan verfasserin aut In Frontiers in Neurorobotics Frontiers Media S.A., 2008 16(2022) (DE-627)579826716 (DE-600)2453002-5 16625218 nnns volume:16 year:2022 https://doi.org/10.3389/fnbot.2022.837208 kostenfrei https://doaj.org/article/19e5af8ada204f8db7352799ee30edba kostenfrei https://www.frontiersin.org/articles/10.3389/fnbot.2022.837208/full kostenfrei https://doaj.org/toc/1662-5218 Journal toc kostenfrei GBV_USEFLAG_A SYSFLAG_A GBV_DOAJ GBV_ILN_11 GBV_ILN_20 GBV_ILN_22 GBV_ILN_23 GBV_ILN_24 GBV_ILN_39 GBV_ILN_40 GBV_ILN_60 GBV_ILN_62 GBV_ILN_63 GBV_ILN_65 GBV_ILN_69 GBV_ILN_70 GBV_ILN_73 GBV_ILN_74 GBV_ILN_95 GBV_ILN_105 GBV_ILN_110 GBV_ILN_151 GBV_ILN_161 GBV_ILN_170 GBV_ILN_206 GBV_ILN_213 GBV_ILN_230 GBV_ILN_285 GBV_ILN_293 GBV_ILN_370 GBV_ILN_602 GBV_ILN_2003 GBV_ILN_2014 GBV_ILN_2055 GBV_ILN_4012 GBV_ILN_4037 GBV_ILN_4112 GBV_ILN_4125 GBV_ILN_4126 GBV_ILN_4249 GBV_ILN_4305 GBV_ILN_4306 GBV_ILN_4307 GBV_ILN_4313 GBV_ILN_4322 GBV_ILN_4323 GBV_ILN_4324 GBV_ILN_4325 GBV_ILN_4335 GBV_ILN_4338 GBV_ILN_4367 GBV_ILN_4700 AR 16 2022
allfieldsSound	10.3389/fnbot.2022.837208 doi (DE-627)DOAJ018075266 (DE-599)DOAJ19e5af8ada204f8db7352799ee30edba DE-627 ger DE-627 rakwb eng RC321-571 HengShuai Cui verfasserin aut Attention-Guided Multi-Scale Feature Fusion Network for Low-Light Image Enhancement 2022 Text txt rdacontent Computermedien c rdamedia Online-Ressource cr rdacarrier Low-light image enhancement has been an important research branch in the field of computer vision. Low-light images are characterized by poor visibility, high noise and low contrast. To improve low-light images generated in low-light environments and night conditions, we propose an Attention-Guided Multi-scale feature fusion network (MSFFNet) for low-light image enhancement for enhancing the contrast and brightness of low-light images. First, to avoid the high cost computation arising from the stacking of multiple sub-networks, our network uses a single encoder and decoder for multi-scale input and output images. Multi-scale input images can make up for the lack of pixel information and loss of feature map information caused by a single input image. The multi-scale output image can effectively monitor the error loss in the image reconstruction process. Second, the Convolutional Block Attention Module (CBAM) is introduced in the encoder part to effectively suppress the noise and color difference generated during feature extraction and further guide the network to refine the color features. Feature calibration module (FCM) is introduced in the decoder section to enhance the mapping expression between channels. Attention fusion module (AFM) is also added to capture contextual information, which is more conducive to recovering image detail information. Last, the cascade fusion module (CFM) is introduced to effectively combine the feature map information under different perceptual fields. Sufficient qualitative and quantitative experiments have been conducted on a variety of publicly available datasets, and the proposed MSFFNet outperforms other low-light enhancement methods in terms of visual effects and metric scores. low-light image enhancement multi-scale attention mechanism feature calibration cascade fusion coarse-to-fine Neurosciences. Biological psychiatry. Neuropsychiatry Jinjiang Li verfasserin aut Jinjiang Li verfasserin aut Zhen Hua verfasserin aut Zhen Hua verfasserin aut Linwei Fan verfasserin aut In Frontiers in Neurorobotics Frontiers Media S.A., 2008 16(2022) (DE-627)579826716 (DE-600)2453002-5 16625218 nnns volume:16 year:2022 https://doi.org/10.3389/fnbot.2022.837208 kostenfrei https://doaj.org/article/19e5af8ada204f8db7352799ee30edba kostenfrei https://www.frontiersin.org/articles/10.3389/fnbot.2022.837208/full kostenfrei https://doaj.org/toc/1662-5218 Journal toc kostenfrei GBV_USEFLAG_A SYSFLAG_A GBV_DOAJ GBV_ILN_11 GBV_ILN_20 GBV_ILN_22 GBV_ILN_23 GBV_ILN_24 GBV_ILN_39 GBV_ILN_40 GBV_ILN_60 GBV_ILN_62 GBV_ILN_63 GBV_ILN_65 GBV_ILN_69 GBV_ILN_70 GBV_ILN_73 GBV_ILN_74 GBV_ILN_95 GBV_ILN_105 GBV_ILN_110 GBV_ILN_151 GBV_ILN_161 GBV_ILN_170 GBV_ILN_206 GBV_ILN_213 GBV_ILN_230 GBV_ILN_285 GBV_ILN_293 GBV_ILN_370 GBV_ILN_602 GBV_ILN_2003 GBV_ILN_2014 GBV_ILN_2055 GBV_ILN_4012 GBV_ILN_4037 GBV_ILN_4112 GBV_ILN_4125 GBV_ILN_4126 GBV_ILN_4249 GBV_ILN_4305 GBV_ILN_4306 GBV_ILN_4307 GBV_ILN_4313 GBV_ILN_4322 GBV_ILN_4323 GBV_ILN_4324 GBV_ILN_4325 GBV_ILN_4335 GBV_ILN_4338 GBV_ILN_4367 GBV_ILN_4700 AR 16 2022
language	English
source	In Frontiers in Neurorobotics 16(2022) volume:16 year:2022
sourceStr	In Frontiers in Neurorobotics 16(2022) volume:16 year:2022
format_phy_str_mv	Article
institution	findex.gbv.de
topic_facet	low-light image enhancement multi-scale attention mechanism feature calibration cascade fusion coarse-to-fine Neurosciences. Biological psychiatry. Neuropsychiatry
isfreeaccess_bool	true
container_title	Frontiers in Neurorobotics
authorswithroles_txt_mv	HengShuai Cui @@aut@@ Jinjiang Li @@aut@@ Zhen Hua @@aut@@ Linwei Fan @@aut@@
publishDateDaySort_date	2022-01-01T00:00:00Z
hierarchy_top_id	579826716
id	DOAJ018075266
language_de	englisch
fullrecord	<?xml version="1.0" encoding="UTF-8"?><collection xmlns="http://www.loc.gov/MARC21/slim"><record><leader>01000caa a22002652 4500</leader><controlfield tag="001">DOAJ018075266</controlfield><controlfield tag="003">DE-627</controlfield><controlfield tag="005">20230310094327.0</controlfield><controlfield tag="007">cr uuu---uuuuu</controlfield><controlfield tag="008">230226s2022 xx \|\|\|\|\|o 00\| \|\|eng c</controlfield><datafield tag="024" ind1="7" ind2=" "><subfield code="a">10.3389/fnbot.2022.837208</subfield><subfield code="2">doi</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-627)DOAJ018075266</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-599)DOAJ19e5af8ada204f8db7352799ee30edba</subfield></datafield><datafield tag="040" ind1=" " ind2=" "><subfield code="a">DE-627</subfield><subfield code="b">ger</subfield><subfield code="c">DE-627</subfield><subfield code="e">rakwb</subfield></datafield><datafield tag="041" ind1=" " ind2=" "><subfield code="a">eng</subfield></datafield><datafield tag="050" ind1=" " ind2="0"><subfield code="a">RC321-571</subfield></datafield><datafield tag="100" ind1="0" ind2=" "><subfield code="a">HengShuai Cui</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="245" ind1="1" ind2="0"><subfield code="a">Attention-Guided Multi-Scale Feature Fusion Network for Low-Light Image Enhancement</subfield></datafield><datafield tag="264" ind1=" " ind2="1"><subfield code="c">2022</subfield></datafield><datafield tag="336" ind1=" " ind2=" "><subfield code="a">Text</subfield><subfield code="b">txt</subfield><subfield code="2">rdacontent</subfield></datafield><datafield tag="337" ind1=" " ind2=" "><subfield code="a">Computermedien</subfield><subfield code="b">c</subfield><subfield code="2">rdamedia</subfield></datafield><datafield tag="338" ind1=" " ind2=" "><subfield code="a">Online-Ressource</subfield><subfield code="b">cr</subfield><subfield code="2">rdacarrier</subfield></datafield><datafield tag="520" ind1=" " ind2=" "><subfield code="a">Low-light image enhancement has been an important research branch in the field of computer vision. Low-light images are characterized by poor visibility, high noise and low contrast. To improve low-light images generated in low-light environments and night conditions, we propose an Attention-Guided Multi-scale feature fusion network (MSFFNet) for low-light image enhancement for enhancing the contrast and brightness of low-light images. First, to avoid the high cost computation arising from the stacking of multiple sub-networks, our network uses a single encoder and decoder for multi-scale input and output images. Multi-scale input images can make up for the lack of pixel information and loss of feature map information caused by a single input image. The multi-scale output image can effectively monitor the error loss in the image reconstruction process. Second, the Convolutional Block Attention Module (CBAM) is introduced in the encoder part to effectively suppress the noise and color difference generated during feature extraction and further guide the network to refine the color features. Feature calibration module (FCM) is introduced in the decoder section to enhance the mapping expression between channels. Attention fusion module (AFM) is also added to capture contextual information, which is more conducive to recovering image detail information. Last, the cascade fusion module (CFM) is introduced to effectively combine the feature map information under different perceptual fields. Sufficient qualitative and quantitative experiments have been conducted on a variety of publicly available datasets, and the proposed MSFFNet outperforms other low-light enhancement methods in terms of visual effects and metric scores.</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">low-light image enhancement</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">multi-scale</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">attention mechanism</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">feature calibration</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">cascade fusion</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">coarse-to-fine</subfield></datafield><datafield tag="653" ind1=" " ind2="0"><subfield code="a">Neurosciences. Biological psychiatry. Neuropsychiatry</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Jinjiang Li</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Jinjiang Li</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Zhen Hua</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Zhen Hua</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Linwei Fan</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="773" ind1="0" ind2="8"><subfield code="i">In</subfield><subfield code="t">Frontiers in Neurorobotics</subfield><subfield code="d">Frontiers Media S.A., 2008</subfield><subfield code="g">16(2022)</subfield><subfield code="w">(DE-627)579826716</subfield><subfield code="w">(DE-600)2453002-5</subfield><subfield code="x">16625218</subfield><subfield code="7">nnns</subfield></datafield><datafield tag="773" ind1="1" ind2="8"><subfield code="g">volume:16</subfield><subfield code="g">year:2022</subfield></datafield><datafield tag="856" ind1="4" ind2="0"><subfield code="u">https://doi.org/10.3389/fnbot.2022.837208</subfield><subfield code="z">kostenfrei</subfield></datafield><datafield tag="856" ind1="4" ind2="0"><subfield code="u">https://doaj.org/article/19e5af8ada204f8db7352799ee30edba</subfield><subfield code="z">kostenfrei</subfield></datafield><datafield tag="856" ind1="4" ind2="0"><subfield code="u">https://www.frontiersin.org/articles/10.3389/fnbot.2022.837208/full</subfield><subfield code="z">kostenfrei</subfield></datafield><datafield tag="856" ind1="4" ind2="2"><subfield code="u">https://doaj.org/toc/1662-5218</subfield><subfield code="y">Journal toc</subfield><subfield code="z">kostenfrei</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_USEFLAG_A</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">SYSFLAG_A</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_DOAJ</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_11</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_20</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_22</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_23</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_24</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_39</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_40</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_60</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_62</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_63</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_65</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_69</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_70</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_73</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_74</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_95</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_105</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_110</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_151</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_161</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_170</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_206</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_213</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_230</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_285</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_293</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_370</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_602</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2003</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2014</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2055</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4012</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4037</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4112</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4125</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4126</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4249</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4305</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4306</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4307</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4313</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4322</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4323</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4324</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4325</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4335</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4338</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4367</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4700</subfield></datafield><datafield tag="951" ind1=" " ind2=" "><subfield code="a">AR</subfield></datafield><datafield tag="952" ind1=" " ind2=" "><subfield code="d">16</subfield><subfield code="j">2022</subfield></datafield></record></collection>
callnumber-first	R - Medicine
author	HengShuai Cui
spellingShingle	HengShuai Cui misc RC321-571 misc low-light image enhancement misc multi-scale misc attention mechanism misc feature calibration misc cascade fusion misc coarse-to-fine misc Neurosciences. Biological psychiatry. Neuropsychiatry Attention-Guided Multi-Scale Feature Fusion Network for Low-Light Image Enhancement
authorStr	HengShuai Cui
ppnlink_with_tag_str_mv	@@773@@(DE-627)579826716
format	electronic Article
delete_txt_mv	keep
author_role	aut aut aut aut aut aut
collection	DOAJ
remote_str	true
callnumber-label	RC321-571
illustrated	Not Illustrated
issn	16625218
topic_title	RC321-571 Attention-Guided Multi-Scale Feature Fusion Network for Low-Light Image Enhancement low-light image enhancement multi-scale attention mechanism feature calibration cascade fusion coarse-to-fine
topic	misc RC321-571 misc low-light image enhancement misc multi-scale misc attention mechanism misc feature calibration misc cascade fusion misc coarse-to-fine misc Neurosciences. Biological psychiatry. Neuropsychiatry
topic_unstemmed	misc RC321-571 misc low-light image enhancement misc multi-scale misc attention mechanism misc feature calibration misc cascade fusion misc coarse-to-fine misc Neurosciences. Biological psychiatry. Neuropsychiatry
topic_browse	misc RC321-571 misc low-light image enhancement misc multi-scale misc attention mechanism misc feature calibration misc cascade fusion misc coarse-to-fine misc Neurosciences. Biological psychiatry. Neuropsychiatry
format_facet	Elektronische Aufsätze Aufsätze Elektronische Ressource
format_main_str_mv	Text Zeitschrift/Artikel
carriertype_str_mv	cr
hierarchy_parent_title	Frontiers in Neurorobotics
hierarchy_parent_id	579826716
hierarchy_top_title	Frontiers in Neurorobotics
isfreeaccess_txt	true
familylinks_str_mv	(DE-627)579826716 (DE-600)2453002-5
title	Attention-Guided Multi-Scale Feature Fusion Network for Low-Light Image Enhancement
ctrlnum	(DE-627)DOAJ018075266 (DE-599)DOAJ19e5af8ada204f8db7352799ee30edba
title_full	Attention-Guided Multi-Scale Feature Fusion Network for Low-Light Image Enhancement
author_sort	HengShuai Cui
journal	Frontiers in Neurorobotics
journalStr	Frontiers in Neurorobotics
callnumber-first-code	R
lang_code	eng
isOA_bool	true
recordtype	marc
publishDateSort	2022
contenttype_str_mv	txt
author_browse	HengShuai Cui Jinjiang Li Zhen Hua Linwei Fan
container_volume	16
class	RC321-571
format_se	Elektronische Aufsätze
author-letter	HengShuai Cui
doi_str_mv	10.3389/fnbot.2022.837208
author2-role	verfasserin
title_sort	attention-guided multi-scale feature fusion network for low-light image enhancement
callnumber	RC321-571
title_auth	Attention-Guided Multi-Scale Feature Fusion Network for Low-Light Image Enhancement
abstract	Low-light image enhancement has been an important research branch in the field of computer vision. Low-light images are characterized by poor visibility, high noise and low contrast. To improve low-light images generated in low-light environments and night conditions, we propose an Attention-Guided Multi-scale feature fusion network (MSFFNet) for low-light image enhancement for enhancing the contrast and brightness of low-light images. First, to avoid the high cost computation arising from the stacking of multiple sub-networks, our network uses a single encoder and decoder for multi-scale input and output images. Multi-scale input images can make up for the lack of pixel information and loss of feature map information caused by a single input image. The multi-scale output image can effectively monitor the error loss in the image reconstruction process. Second, the Convolutional Block Attention Module (CBAM) is introduced in the encoder part to effectively suppress the noise and color difference generated during feature extraction and further guide the network to refine the color features. Feature calibration module (FCM) is introduced in the decoder section to enhance the mapping expression between channels. Attention fusion module (AFM) is also added to capture contextual information, which is more conducive to recovering image detail information. Last, the cascade fusion module (CFM) is introduced to effectively combine the feature map information under different perceptual fields. Sufficient qualitative and quantitative experiments have been conducted on a variety of publicly available datasets, and the proposed MSFFNet outperforms other low-light enhancement methods in terms of visual effects and metric scores.
abstractGer	Low-light image enhancement has been an important research branch in the field of computer vision. Low-light images are characterized by poor visibility, high noise and low contrast. To improve low-light images generated in low-light environments and night conditions, we propose an Attention-Guided Multi-scale feature fusion network (MSFFNet) for low-light image enhancement for enhancing the contrast and brightness of low-light images. First, to avoid the high cost computation arising from the stacking of multiple sub-networks, our network uses a single encoder and decoder for multi-scale input and output images. Multi-scale input images can make up for the lack of pixel information and loss of feature map information caused by a single input image. The multi-scale output image can effectively monitor the error loss in the image reconstruction process. Second, the Convolutional Block Attention Module (CBAM) is introduced in the encoder part to effectively suppress the noise and color difference generated during feature extraction and further guide the network to refine the color features. Feature calibration module (FCM) is introduced in the decoder section to enhance the mapping expression between channels. Attention fusion module (AFM) is also added to capture contextual information, which is more conducive to recovering image detail information. Last, the cascade fusion module (CFM) is introduced to effectively combine the feature map information under different perceptual fields. Sufficient qualitative and quantitative experiments have been conducted on a variety of publicly available datasets, and the proposed MSFFNet outperforms other low-light enhancement methods in terms of visual effects and metric scores.
abstract_unstemmed	Low-light image enhancement has been an important research branch in the field of computer vision. Low-light images are characterized by poor visibility, high noise and low contrast. To improve low-light images generated in low-light environments and night conditions, we propose an Attention-Guided Multi-scale feature fusion network (MSFFNet) for low-light image enhancement for enhancing the contrast and brightness of low-light images. First, to avoid the high cost computation arising from the stacking of multiple sub-networks, our network uses a single encoder and decoder for multi-scale input and output images. Multi-scale input images can make up for the lack of pixel information and loss of feature map information caused by a single input image. The multi-scale output image can effectively monitor the error loss in the image reconstruction process. Second, the Convolutional Block Attention Module (CBAM) is introduced in the encoder part to effectively suppress the noise and color difference generated during feature extraction and further guide the network to refine the color features. Feature calibration module (FCM) is introduced in the decoder section to enhance the mapping expression between channels. Attention fusion module (AFM) is also added to capture contextual information, which is more conducive to recovering image detail information. Last, the cascade fusion module (CFM) is introduced to effectively combine the feature map information under different perceptual fields. Sufficient qualitative and quantitative experiments have been conducted on a variety of publicly available datasets, and the proposed MSFFNet outperforms other low-light enhancement methods in terms of visual effects and metric scores.
collection_details	GBV_USEFLAG_A SYSFLAG_A GBV_DOAJ GBV_ILN_11 GBV_ILN_20 GBV_ILN_22 GBV_ILN_23 GBV_ILN_24 GBV_ILN_39 GBV_ILN_40 GBV_ILN_60 GBV_ILN_62 GBV_ILN_63 GBV_ILN_65 GBV_ILN_69 GBV_ILN_70 GBV_ILN_73 GBV_ILN_74 GBV_ILN_95 GBV_ILN_105 GBV_ILN_110 GBV_ILN_151 GBV_ILN_161 GBV_ILN_170 GBV_ILN_206 GBV_ILN_213 GBV_ILN_230 GBV_ILN_285 GBV_ILN_293 GBV_ILN_370 GBV_ILN_602 GBV_ILN_2003 GBV_ILN_2014 GBV_ILN_2055 GBV_ILN_4012 GBV_ILN_4037 GBV_ILN_4112 GBV_ILN_4125 GBV_ILN_4126 GBV_ILN_4249 GBV_ILN_4305 GBV_ILN_4306 GBV_ILN_4307 GBV_ILN_4313 GBV_ILN_4322 GBV_ILN_4323 GBV_ILN_4324 GBV_ILN_4325 GBV_ILN_4335 GBV_ILN_4338 GBV_ILN_4367 GBV_ILN_4700
title_short	Attention-Guided Multi-Scale Feature Fusion Network for Low-Light Image Enhancement
url	https://doi.org/10.3389/fnbot.2022.837208 https://doaj.org/article/19e5af8ada204f8db7352799ee30edba https://www.frontiersin.org/articles/10.3389/fnbot.2022.837208/full https://doaj.org/toc/1662-5218
remote_bool	true
author2	Jinjiang Li Zhen Hua Linwei Fan
author2Str	Jinjiang Li Zhen Hua Linwei Fan
ppnlink	579826716
callnumber-subject	RC - Internal Medicine
mediatype_str_mv	c
isOA_txt	true
hochschulschrift_bool	false
doi_str	10.3389/fnbot.2022.837208
callnumber-a	RC321-571
up_date	2024-07-03T15:48:07.235Z
_version_	1803573460715175936
fullrecord_marcxml	<?xml version="1.0" encoding="UTF-8"?><collection xmlns="http://www.loc.gov/MARC21/slim"><record><leader>01000caa a22002652 4500</leader><controlfield tag="001">DOAJ018075266</controlfield><controlfield tag="003">DE-627</controlfield><controlfield tag="005">20230310094327.0</controlfield><controlfield tag="007">cr uuu---uuuuu</controlfield><controlfield tag="008">230226s2022 xx \|\|\|\|\|o 00\| \|\|eng c</controlfield><datafield tag="024" ind1="7" ind2=" "><subfield code="a">10.3389/fnbot.2022.837208</subfield><subfield code="2">doi</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-627)DOAJ018075266</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-599)DOAJ19e5af8ada204f8db7352799ee30edba</subfield></datafield><datafield tag="040" ind1=" " ind2=" "><subfield code="a">DE-627</subfield><subfield code="b">ger</subfield><subfield code="c">DE-627</subfield><subfield code="e">rakwb</subfield></datafield><datafield tag="041" ind1=" " ind2=" "><subfield code="a">eng</subfield></datafield><datafield tag="050" ind1=" " ind2="0"><subfield code="a">RC321-571</subfield></datafield><datafield tag="100" ind1="0" ind2=" "><subfield code="a">HengShuai Cui</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="245" ind1="1" ind2="0"><subfield code="a">Attention-Guided Multi-Scale Feature Fusion Network for Low-Light Image Enhancement</subfield></datafield><datafield tag="264" ind1=" " ind2="1"><subfield code="c">2022</subfield></datafield><datafield tag="336" ind1=" " ind2=" "><subfield code="a">Text</subfield><subfield code="b">txt</subfield><subfield code="2">rdacontent</subfield></datafield><datafield tag="337" ind1=" " ind2=" "><subfield code="a">Computermedien</subfield><subfield code="b">c</subfield><subfield code="2">rdamedia</subfield></datafield><datafield tag="338" ind1=" " ind2=" "><subfield code="a">Online-Ressource</subfield><subfield code="b">cr</subfield><subfield code="2">rdacarrier</subfield></datafield><datafield tag="520" ind1=" " ind2=" "><subfield code="a">Low-light image enhancement has been an important research branch in the field of computer vision. Low-light images are characterized by poor visibility, high noise and low contrast. To improve low-light images generated in low-light environments and night conditions, we propose an Attention-Guided Multi-scale feature fusion network (MSFFNet) for low-light image enhancement for enhancing the contrast and brightness of low-light images. First, to avoid the high cost computation arising from the stacking of multiple sub-networks, our network uses a single encoder and decoder for multi-scale input and output images. Multi-scale input images can make up for the lack of pixel information and loss of feature map information caused by a single input image. The multi-scale output image can effectively monitor the error loss in the image reconstruction process. Second, the Convolutional Block Attention Module (CBAM) is introduced in the encoder part to effectively suppress the noise and color difference generated during feature extraction and further guide the network to refine the color features. Feature calibration module (FCM) is introduced in the decoder section to enhance the mapping expression between channels. Attention fusion module (AFM) is also added to capture contextual information, which is more conducive to recovering image detail information. Last, the cascade fusion module (CFM) is introduced to effectively combine the feature map information under different perceptual fields. Sufficient qualitative and quantitative experiments have been conducted on a variety of publicly available datasets, and the proposed MSFFNet outperforms other low-light enhancement methods in terms of visual effects and metric scores.</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">low-light image enhancement</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">multi-scale</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">attention mechanism</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">feature calibration</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">cascade fusion</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">coarse-to-fine</subfield></datafield><datafield tag="653" ind1=" " ind2="0"><subfield code="a">Neurosciences. Biological psychiatry. Neuropsychiatry</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Jinjiang Li</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Jinjiang Li</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Zhen Hua</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Zhen Hua</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Linwei Fan</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="773" ind1="0" ind2="8"><subfield code="i">In</subfield><subfield code="t">Frontiers in Neurorobotics</subfield><subfield code="d">Frontiers Media S.A., 2008</subfield><subfield code="g">16(2022)</subfield><subfield code="w">(DE-627)579826716</subfield><subfield code="w">(DE-600)2453002-5</subfield><subfield code="x">16625218</subfield><subfield code="7">nnns</subfield></datafield><datafield tag="773" ind1="1" ind2="8"><subfield code="g">volume:16</subfield><subfield code="g">year:2022</subfield></datafield><datafield tag="856" ind1="4" ind2="0"><subfield code="u">https://doi.org/10.3389/fnbot.2022.837208</subfield><subfield code="z">kostenfrei</subfield></datafield><datafield tag="856" ind1="4" ind2="0"><subfield code="u">https://doaj.org/article/19e5af8ada204f8db7352799ee30edba</subfield><subfield code="z">kostenfrei</subfield></datafield><datafield tag="856" ind1="4" ind2="0"><subfield code="u">https://www.frontiersin.org/articles/10.3389/fnbot.2022.837208/full</subfield><subfield code="z">kostenfrei</subfield></datafield><datafield tag="856" ind1="4" ind2="2"><subfield code="u">https://doaj.org/toc/1662-5218</subfield><subfield code="y">Journal toc</subfield><subfield code="z">kostenfrei</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_USEFLAG_A</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">SYSFLAG_A</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_DOAJ</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_11</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_20</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_22</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_23</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_24</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_39</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_40</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_60</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_62</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_63</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_65</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_69</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_70</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_73</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_74</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_95</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_105</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_110</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_151</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_161</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_170</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_206</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_213</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_230</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_285</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_293</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_370</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_602</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2003</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2014</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2055</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4012</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4037</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4112</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4125</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4126</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4249</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4305</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4306</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4307</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4313</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4322</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4323</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4324</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4325</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4335</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4338</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4367</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4700</subfield></datafield><datafield tag="951" ind1=" " ind2=" "><subfield code="a">AR</subfield></datafield><datafield tag="952" ind1=" " ind2=" "><subfield code="d">16</subfield><subfield code="j">2022</subfield></datafield></record></collection>
score	7.4000835

Nicht das Richtige dabei?

Schreiben Sie uns!

Attention-Guided Multi-Scale Feature Fusion Network for Low-Light Image Enhancement

Nicht das Richtige dabei?

Zugang & Verfügbarkeit

Vorhandene Bände

Nicht das Richtige dabei?