Matches in SemOpenAlex for { <https://semopenalex.org/work/W4313387504> ?p ?o ?g. }
- W4313387504 abstract "The images captured under low-light conditions are characterized by low brightness and poor contrast, which affects the accuracy of computer vision tasks. In recent years, there have been a variety of low-light image enhancement (LLIE) models based on deep learning, but they have not been able to fully extract the multiscale information of multiple stages, resulting in poor generalization performance and instability of the model. Currently, a large number of multistage networks cause color distortion and stylization of images due to excessive transmission of noncritical information. To address these issues, we propose an LLIE via multistage feature fusion network. Our network consists of three stages. In the first two stages of the LLIE, S-UNet, which combines UNet and spatial weighted residual channel attention block (SWRCAB), helps the network extract more critical multiscale information and occupy a small amount of computing resources. In the third stage, we fuse the SWRCAB and a nonlocal sparse block into the original enhancement network to enhance the original resolution pixel-by-pixel. We also propose a fusion attention mechanism, which can provide real and effective supervision and control the transmission of a small amount of critical feature information for each stage. In addition, we add illumination guidance for image segmentation at the beginning of each stage of the network, excepting that the model can better focus on the dark part of the low-light image and avoid overexposure. We conduct experiments on multiple benchmark datasets to qualitatively and quantitatively demonstrate that the proposed method is more competitive than the state-of-the-art methods." @default.
- W4313387504 created "2023-01-06" @default.
- W4313387504 creator A5012984188 @default.
- W4313387504 creator A5016244288 @default.
- W4313387504 creator A5035975139 @default.
- W4313387504 creator A5047001937 @default.
- W4313387504 date "2022-12-19" @default.
- W4313387504 modified "2023-10-01" @default.
- W4313387504 title "Low-light image enhancement via multistage feature fusion network" @default.
- W4313387504 cites W1580436348 @default.
- W4313387504 cites W1986086122 @default.
- W4313387504 cites W1987444808 @default.
- W4313387504 cites W2012554041 @default.
- W4313387504 cites W2054814429 @default.
- W4313387504 cites W2058333183 @default.
- W4313387504 cites W2102166818 @default.
- W4313387504 cites W2108598243 @default.
- W4313387504 cites W2109616376 @default.
- W4313387504 cites W2121900453 @default.
- W4313387504 cites W2139375301 @default.
- W4313387504 cites W2147421915 @default.
- W4313387504 cites W2164847484 @default.
- W4313387504 cites W2165107586 @default.
- W4313387504 cites W2752782242 @default.
- W4313387504 cites W2783399029 @default.
- W4313387504 cites W2783573276 @default.
- W4313387504 cites W2954930822 @default.
- W4313387504 cites W2963228457 @default.
- W4313387504 cites W2963766909 @default.
- W4313387504 cites W3003838261 @default.
- W4313387504 cites W3015360456 @default.
- W4313387504 cites W3034789174 @default.
- W4313387504 cites W3035326127 @default.
- W4313387504 cites W3035631962 @default.
- W4313387504 cites W3119456559 @default.
- W4313387504 cites W3120540810 @default.
- W4313387504 cites W3129497682 @default.
- W4313387504 cites W3159250660 @default.
- W4313387504 cites W3161911147 @default.
- W4313387504 cites W3174531399 @default.
- W4313387504 cites W3174792937 @default.
- W4313387504 cites W4213256221 @default.
- W4313387504 cites W4226096992 @default.
- W4313387504 cites W4283712710 @default.
- W4313387504 cites W4283789008 @default.
- W4313387504 cites W4284666140 @default.
- W4313387504 cites W4285011353 @default.
- W4313387504 cites W4285025661 @default.
- W4313387504 cites W4293233622 @default.
- W4313387504 cites W4313059954 @default.
- W4313387504 doi "https://doi.org/10.1117/1.jei.31.6.063050" @default.
- W4313387504 hasPublicationYear "2022" @default.
- W4313387504 type Work @default.
- W4313387504 citedByCount "1" @default.
- W4313387504 countsByYear W43133875042023 @default.
- W4313387504 crossrefType "journal-article" @default.
- W4313387504 hasAuthorship W4313387504A5012984188 @default.
- W4313387504 hasAuthorship W4313387504A5016244288 @default.
- W4313387504 hasAuthorship W4313387504A5035975139 @default.
- W4313387504 hasAuthorship W4313387504A5047001937 @default.
- W4313387504 hasConcept C11413529 @default.
- W4313387504 hasConcept C115961682 @default.
- W4313387504 hasConcept C119599485 @default.
- W4313387504 hasConcept C120665830 @default.
- W4313387504 hasConcept C121332964 @default.
- W4313387504 hasConcept C126780896 @default.
- W4313387504 hasConcept C127413603 @default.
- W4313387504 hasConcept C13280743 @default.
- W4313387504 hasConcept C138885662 @default.
- W4313387504 hasConcept C141353440 @default.
- W4313387504 hasConcept C153180895 @default.
- W4313387504 hasConcept C154945302 @default.
- W4313387504 hasConcept C155512373 @default.
- W4313387504 hasConcept C160633673 @default.
- W4313387504 hasConcept C185798385 @default.
- W4313387504 hasConcept C192209626 @default.
- W4313387504 hasConcept C194257627 @default.
- W4313387504 hasConcept C205649164 @default.
- W4313387504 hasConcept C2524010 @default.
- W4313387504 hasConcept C2776257435 @default.
- W4313387504 hasConcept C2776401178 @default.
- W4313387504 hasConcept C2777210771 @default.
- W4313387504 hasConcept C31258907 @default.
- W4313387504 hasConcept C31972630 @default.
- W4313387504 hasConcept C33923547 @default.
- W4313387504 hasConcept C41008148 @default.
- W4313387504 hasConcept C41895202 @default.
- W4313387504 hasConcept C52622490 @default.
- W4313387504 hasConcept C69744172 @default.
- W4313387504 hasConceptScore W4313387504C11413529 @default.
- W4313387504 hasConceptScore W4313387504C115961682 @default.
- W4313387504 hasConceptScore W4313387504C119599485 @default.
- W4313387504 hasConceptScore W4313387504C120665830 @default.
- W4313387504 hasConceptScore W4313387504C121332964 @default.
- W4313387504 hasConceptScore W4313387504C126780896 @default.
- W4313387504 hasConceptScore W4313387504C127413603 @default.
- W4313387504 hasConceptScore W4313387504C13280743 @default.
- W4313387504 hasConceptScore W4313387504C138885662 @default.
- W4313387504 hasConceptScore W4313387504C141353440 @default.
- W4313387504 hasConceptScore W4313387504C153180895 @default.