Matches in SemOpenAlex for { <https://semopenalex.org/work/W4323307218> ?p ?o ?g. }
Showing items 1 to 79 of
79
with 100 items per page.
- W4323307218 endingPage "103795" @default.
- W4323307218 startingPage "103795" @default.
- W4323307218 abstract "Most low-light image enhancement methods only adjust the brightness, contrast and noise reduction of low-light images, making it difficult to recover the lost information in darker areas of the image, and even cause color distortion and blurring. To solve the above problems, a global attention-based Retinex network (GARN) for low-light image enhancement is proposed in this paper. We propose a novel global attention module which computes multiple dimensional information in the channel attention module to help facilitate inference learning. Then the global attention module is embedded into different layers of the network to extract richer shallow texture features and deep semantic features. This means that the rich features are more conducive to learning the mapping relationship between low-light images to normal-light images, so that the detail recovery of dark regions is enhanced in low-light images. We also collected a low/normal light image dataset with multiple scenes, in which the images paired as training set can succeed to be applied to low-light image enhancement under different lighting conditions. Experimental results on publicly available datasets show that our method has better effectiveness and generality than the state-of-the-art methods in terms of evaluations metrics such as PSNR, SSIM, NIQE, Entropy." @default.
- W4323307218 created "2023-03-07" @default.
- W4323307218 creator A5028091119 @default.
- W4323307218 creator A5081014401 @default.
- W4323307218 date "2023-04-01" @default.
- W4323307218 modified "2023-10-18" @default.
- W4323307218 title "Global attention retinex network for low light image enhancement" @default.
- W4323307218 cites W1987444808 @default.
- W4323307218 cites W2054814429 @default.
- W4323307218 cites W2076205488 @default.
- W4323307218 cites W2102166818 @default.
- W4323307218 cites W2133665775 @default.
- W4323307218 cites W2254039850 @default.
- W4323307218 cites W2412926690 @default.
- W4323307218 cites W2566376500 @default.
- W4323307218 cites W2735974062 @default.
- W4323307218 cites W2752782242 @default.
- W4323307218 cites W2783399029 @default.
- W4323307218 cites W2783573276 @default.
- W4323307218 cites W2791710889 @default.
- W4323307218 cites W2884585870 @default.
- W4323307218 cites W2981718299 @default.
- W4323307218 cites W3035297694 @default.
- W4323307218 cites W3093427603 @default.
- W4323307218 cites W3119026898 @default.
- W4323307218 cites W3120540810 @default.
- W4323307218 cites W3124426233 @default.
- W4323307218 cites W3137277224 @default.
- W4323307218 cites W4205985764 @default.
- W4323307218 cites W4312249431 @default.
- W4323307218 cites W4312725970 @default.
- W4323307218 doi "https://doi.org/10.1016/j.jvcir.2023.103795" @default.
- W4323307218 hasPublicationYear "2023" @default.
- W4323307218 type Work @default.
- W4323307218 citedByCount "2" @default.
- W4323307218 countsByYear W43233072182023 @default.
- W4323307218 crossrefType "journal-article" @default.
- W4323307218 hasAuthorship W4323307218A5028091119 @default.
- W4323307218 hasAuthorship W4323307218A5081014401 @default.
- W4323307218 hasBestOaLocation W43233072181 @default.
- W4323307218 hasConcept C115961682 @default.
- W4323307218 hasConcept C120665830 @default.
- W4323307218 hasConcept C121332964 @default.
- W4323307218 hasConcept C125245961 @default.
- W4323307218 hasConcept C153180895 @default.
- W4323307218 hasConcept C154945302 @default.
- W4323307218 hasConcept C187888035 @default.
- W4323307218 hasConcept C31972630 @default.
- W4323307218 hasConcept C41008148 @default.
- W4323307218 hasConceptScore W4323307218C115961682 @default.
- W4323307218 hasConceptScore W4323307218C120665830 @default.
- W4323307218 hasConceptScore W4323307218C121332964 @default.
- W4323307218 hasConceptScore W4323307218C125245961 @default.
- W4323307218 hasConceptScore W4323307218C153180895 @default.
- W4323307218 hasConceptScore W4323307218C154945302 @default.
- W4323307218 hasConceptScore W4323307218C187888035 @default.
- W4323307218 hasConceptScore W4323307218C31972630 @default.
- W4323307218 hasConceptScore W4323307218C41008148 @default.
- W4323307218 hasFunder F4320321001 @default.
- W4323307218 hasFunder F4320321494 @default.
- W4323307218 hasLocation W43233072181 @default.
- W4323307218 hasOpenAccess W4323307218 @default.
- W4323307218 hasPrimaryLocation W43233072181 @default.
- W4323307218 hasRelatedWork W1603973577 @default.
- W4323307218 hasRelatedWork W2006198159 @default.
- W4323307218 hasRelatedWork W2082294883 @default.
- W4323307218 hasRelatedWork W2114667878 @default.
- W4323307218 hasRelatedWork W2159871081 @default.
- W4323307218 hasRelatedWork W2387055199 @default.
- W4323307218 hasRelatedWork W2622554317 @default.
- W4323307218 hasRelatedWork W2796466323 @default.
- W4323307218 hasRelatedWork W2982638676 @default.
- W4323307218 hasRelatedWork W4237735386 @default.
- W4323307218 hasVolume "92" @default.
- W4323307218 isParatext "false" @default.
- W4323307218 isRetracted "false" @default.
- W4323307218 workType "article" @default.