FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4312757619> ?p ?o ?g. }

• W4312757619 endingPage "18" @default.
• W4312757619 startingPage "1" @default.
• W4312757619 abstract "Images captured in low light and backlit conditions are characterized by low brightness, low contrast, and varying degrees of degradation. Simply enhancing image contrast will fully expose hidden noise and color distortion, affecting people’s subjective visual perception and performance in other application scenarios. In order to improve the loss of details, color imbalance and artifacts in the enhanced images, we propose a progressive dual branch network(PDBNet) for low-light image enhancement. In this paper, an assisted recovery module(ARM) is designed by exploiting the hybrid correlation and feature complementarity between the inverted image and the low-light image. Feature information at different scales is progressively extracted by cascading multiple ARMs. Considering the network execution efficiency and the amount of parameters, we use depthwise separable convolution(DSC) and asymmetric assisted recovery module(ARM) to improve the computational efficiency of the model. To reduce the degradation caused by enhancing image contrast, the introduction of the large kernel attention(LKA) block allows the network to emphasize hidden low-light information regions, effectively suppressing noise and improving color imbalance. In order to effectively fuse the feature information between the inverse image and the low-light image, an attention fusion block(AFB) is designed. AFB can effectively acquire global feature information and re-encode semantic dependencies between channels. Finally, a fusion reconstruction module(FRM) is designed to further refine the feature information and enhance the information flow between networks. After sufficient qualitative and quantitative experiments in publicly available low-light image datasets, it is known that our method has better visual quality and metric evaluation scores than other state-of-the-art low-light image enhancement methods." @default.
• W4312757619 created "2023-01-05" @default.
• W4312757619 creator A5000298140 @default.
• W4312757619 creator A5001915605 @default.
• W4312757619 creator A5028836596 @default.
• W4312757619 creator A5078116487 @default.
• W4312757619 date "2022-01-01" @default.
• W4312757619 modified "2023-10-15" @default.
• W4312757619 title "Progressive Dual-Branch Network for Low-Light Image Enhancement" @default.
• W4312757619 cites W1580436348 @default.
• W4312757619 cites W1976468890 @default.
• W4312757619 cites W1982471090 @default.
• W4312757619 cites W1986086122 @default.
• W4312757619 cites W1987444808 @default.
• W4312757619 cites W2011260964 @default.
• W4312757619 cites W2023218193 @default.
• W4312757619 cites W2038713671 @default.
• W4312757619 cites W2054814429 @default.
• W4312757619 cites W2058333183 @default.
• W4312757619 cites W2074227110 @default.
• W4312757619 cites W2090938122 @default.
• W4312757619 cites W2102166818 @default.
• W4312757619 cites W2121900453 @default.
• W4312757619 cites W2124843241 @default.
• W4312757619 cites W2126926806 @default.
• W4312757619 cites W2141983208 @default.
• W4312757619 cites W2150721269 @default.
• W4312757619 cites W2154549868 @default.
• W4312757619 cites W2157095036 @default.
• W4312757619 cites W2254039850 @default.
• W4312757619 cites W2296548841 @default.
• W4312757619 cites W2468596194 @default.
• W4312757619 cites W2471157114 @default.
• W4312757619 cites W2566376500 @default.
• W4312757619 cites W2601040106 @default.
• W4312757619 cites W2610602405 @default.
• W4312757619 cites W2752782242 @default.
• W4312757619 cites W2768814045 @default.
• W4312757619 cites W2791710889 @default.
• W4312757619 cites W2798844427 @default.
• W4312757619 cites W2799265886 @default.
• W4312757619 cites W2807563922 @default.
• W4312757619 cites W2883618893 @default.
• W4312757619 cites W2941572835 @default.
• W4312757619 cites W2947137735 @default.
• W4312757619 cites W2955058313 @default.
• W4312757619 cites W2962772649 @default.
• W4312757619 cites W2962785568 @default.
• W4312757619 cites W2963091558 @default.
• W4312757619 cites W2963182372 @default.
• W4312757619 cites W2981718299 @default.
• W4312757619 cites W2990007814 @default.
• W4312757619 cites W3003838261 @default.
• W4312757619 cites W3034347506 @default.
• W4312757619 cites W3035051775 @default.
• W4312757619 cites W3035731588 @default.
• W4312757619 cites W3042993386 @default.
• W4312757619 cites W3095495550 @default.
• W4312757619 cites W3106758205 @default.
• W4312757619 cites W3121661546 @default.
• W4312757619 cites W3127242989 @default.
• W4312757619 cites W3131500599 @default.
• W4312757619 cites W3135934332 @default.
• W4312757619 cites W3136937830 @default.
• W4312757619 cites W3139633126 @default.
• W4312757619 cites W3151130473 @default.
• W4312757619 cites W3159481202 @default.
• W4312757619 cites W3167095230 @default.
• W4312757619 cites W3173269149 @default.
• W4312757619 cites W3175958943 @default.
• W4312757619 cites W3176148916 @default.
• W4312757619 cites W3178960106 @default.
• W4312757619 cites W3180134609 @default.
• W4312757619 cites W4242043970 @default.
• W4312757619 doi "https://doi.org/10.1109/tim.2022.3216880" @default.
• W4312757619 hasPublicationYear "2022" @default.
• W4312757619 type Work @default.
• W4312757619 citedByCount "2" @default.
• W4312757619 countsByYear W43127576192023 @default.
• W4312757619 crossrefType "journal-article" @default.
• W4312757619 hasAuthorship W4312757619A5000298140 @default.
• W4312757619 hasAuthorship W4312757619A5001915605 @default.
• W4312757619 hasAuthorship W4312757619A5028836596 @default.
• W4312757619 hasAuthorship W4312757619A5078116487 @default.
• W4312757619 hasConcept C114614502 @default.
• W4312757619 hasConcept C138885662 @default.
• W4312757619 hasConcept C153180895 @default.
• W4312757619 hasConcept C154945302 @default.
• W4312757619 hasConcept C2524010 @default.
• W4312757619 hasConcept C2776401178 @default.
• W4312757619 hasConcept C2777210771 @default.
• W4312757619 hasConcept C31972630 @default.
• W4312757619 hasConcept C33923547 @default.
• W4312757619 hasConcept C41008148 @default.
• W4312757619 hasConcept C41895202 @default.
• W4312757619 hasConcept C74193536 @default.
• W4312757619 hasConceptScore W4312757619C114614502 @default.
• W4312757619 hasConceptScore W4312757619C138885662 @default.

• next