Matches in SemOpenAlex for { <https://semopenalex.org/work/W4361273774> ?p ?o ?g. }
Showing items 1 to 97 of
97
with 100 items per page.
- W4361273774 endingPage "1657" @default.
- W4361273774 startingPage "1657" @default.
- W4361273774 abstract "Within low-light imaging environment, the insufficient reflected light from objects often results in unsatisfactory images with degradations of low contrast, noise artifacts, or color distortion. The captured low-light images usually lead to poor visual perception quality for color deficient or normal observers. To address the above problems, we propose an end-to-end low-light image enhancement network by combining transformer and CNN (convolutional neural network) to restore the normal light images. Specifically, the proposed enhancement network is designed into a U-shape structure with several functional fusion blocks. Each fusion block includes a transformer stem and a CNN stem, and those two stems collaborate to accurately extract the local and global features. In this way, the transformer stem is responsible for efficiently learning global semantic information and capturing long-term dependencies, while the CNN stem is good at learning local features and focusing on detailed features. Thus, the proposed enhancement network can accurately capture the comprehensive semantic information of low-light images, which significantly contribute to recover normal light images. The proposed method is compared with the current popular algorithms quantitatively and qualitatively. Subjectively, our method significantly improves the image brightness, suppresses the image noise, and maintains the texture details and color information. For objective metrics such as peak signal-to-noise ratio (PSNR), structural similarity (SSIM), image perceptual similarity (LPIPS), DeltaE, and NIQE, our method improves the optimal values by 1.73 dB, 0.05, 0.043, 0.7939, and 0.6906, respectively, compared with other methods. The experimental results show that our proposed method can effectively solve the problems of underexposure, noise interference, and color inconsistency in micro-optical images, and has certain application value." @default.
- W4361273774 created "2023-03-31" @default.
- W4361273774 creator A5018570797 @default.
- W4361273774 creator A5018762110 @default.
- W4361273774 creator A5021092757 @default.
- W4361273774 creator A5021793949 @default.
- W4361273774 creator A5025089494 @default.
- W4361273774 creator A5029936233 @default.
- W4361273774 creator A5070913913 @default.
- W4361273774 date "2023-03-30" @default.
- W4361273774 modified "2023-10-16" @default.
- W4361273774 title "Low-Light Image Enhancement by Combining Transformer and Convolutional Neural Network" @default.
- W4361273774 cites W1580436348 @default.
- W4361273774 cites W1987444808 @default.
- W4361273774 cites W2054814429 @default.
- W4361273774 cites W2102166818 @default.
- W4361273774 cites W2118002060 @default.
- W4361273774 cites W2123585888 @default.
- W4361273774 cites W2133665775 @default.
- W4361273774 cites W2141117074 @default.
- W4361273774 cites W2144628669 @default.
- W4361273774 cites W2150461190 @default.
- W4361273774 cites W2150721269 @default.
- W4361273774 cites W2150969685 @default.
- W4361273774 cites W2169852119 @default.
- W4361273774 cites W2254039850 @default.
- W4361273774 cites W2331128040 @default.
- W4361273774 cites W2566376500 @default.
- W4361273774 cites W2791710889 @default.
- W4361273774 cites W2799265886 @default.
- W4361273774 cites W2807563922 @default.
- W4361273774 cites W2948354154 @default.
- W4361273774 cites W2962785568 @default.
- W4361273774 cites W2963182372 @default.
- W4361273774 cites W2963890956 @default.
- W4361273774 cites W2981718299 @default.
- W4361273774 cites W3035731588 @default.
- W4361273774 cites W3121661546 @default.
- W4361273774 cites W4283021596 @default.
- W4361273774 cites W4283311847 @default.
- W4361273774 cites W4312249431 @default.
- W4361273774 doi "https://doi.org/10.3390/math11071657" @default.
- W4361273774 hasPublicationYear "2023" @default.
- W4361273774 type Work @default.
- W4361273774 citedByCount "1" @default.
- W4361273774 countsByYear W43612737742023 @default.
- W4361273774 crossrefType "journal-article" @default.
- W4361273774 hasAuthorship W4361273774A5018570797 @default.
- W4361273774 hasAuthorship W4361273774A5018762110 @default.
- W4361273774 hasAuthorship W4361273774A5021092757 @default.
- W4361273774 hasAuthorship W4361273774A5021793949 @default.
- W4361273774 hasAuthorship W4361273774A5025089494 @default.
- W4361273774 hasAuthorship W4361273774A5029936233 @default.
- W4361273774 hasAuthorship W4361273774A5070913913 @default.
- W4361273774 hasBestOaLocation W43612737741 @default.
- W4361273774 hasConcept C120665830 @default.
- W4361273774 hasConcept C121332964 @default.
- W4361273774 hasConcept C125245961 @default.
- W4361273774 hasConcept C153180895 @default.
- W4361273774 hasConcept C154945302 @default.
- W4361273774 hasConcept C165801399 @default.
- W4361273774 hasConcept C31972630 @default.
- W4361273774 hasConcept C41008148 @default.
- W4361273774 hasConcept C62520636 @default.
- W4361273774 hasConcept C66322947 @default.
- W4361273774 hasConcept C81363708 @default.
- W4361273774 hasConceptScore W4361273774C120665830 @default.
- W4361273774 hasConceptScore W4361273774C121332964 @default.
- W4361273774 hasConceptScore W4361273774C125245961 @default.
- W4361273774 hasConceptScore W4361273774C153180895 @default.
- W4361273774 hasConceptScore W4361273774C154945302 @default.
- W4361273774 hasConceptScore W4361273774C165801399 @default.
- W4361273774 hasConceptScore W4361273774C31972630 @default.
- W4361273774 hasConceptScore W4361273774C41008148 @default.
- W4361273774 hasConceptScore W4361273774C62520636 @default.
- W4361273774 hasConceptScore W4361273774C66322947 @default.
- W4361273774 hasConceptScore W4361273774C81363708 @default.
- W4361273774 hasIssue "7" @default.
- W4361273774 hasLocation W43612737741 @default.
- W4361273774 hasOpenAccess W4361273774 @default.
- W4361273774 hasPrimaryLocation W43612737741 @default.
- W4361273774 hasRelatedWork W1986038857 @default.
- W4361273774 hasRelatedWork W2012641939 @default.
- W4361273774 hasRelatedWork W2035413902 @default.
- W4361273774 hasRelatedWork W2120516655 @default.
- W4361273774 hasRelatedWork W2575060017 @default.
- W4361273774 hasRelatedWork W2767651786 @default.
- W4361273774 hasRelatedWork W2908959303 @default.
- W4361273774 hasRelatedWork W2912288872 @default.
- W4361273774 hasRelatedWork W3001218575 @default.
- W4361273774 hasRelatedWork W4244517792 @default.
- W4361273774 hasVolume "11" @default.
- W4361273774 isParatext "false" @default.
- W4361273774 isRetracted "false" @default.
- W4361273774 workType "article" @default.