Matches in SemOpenAlex for { <https://semopenalex.org/work/W4293498847> ?p ?o ?g. }
- W4293498847 endingPage "92596" @default.
- W4293498847 startingPage "92583" @default.
- W4293498847 abstract "Low-light images have low brightness and low contrast, which bring huge obstacles to the intelligent video surveillance system. The enhancement of low-light images must simultaneously consider the interference of factors such as brightness, contrast, artifacts, and noise. To this end, in this study, we propose a gradient prior-aided low-light enhancement network (GPANet). The main idea is to improve the network's ability to extract edge features and remove unwanted noise by introducing first-order (i.e., Sobel Filter) and second-order gradient (i.e., Laplacian Filter) features. Unlike in previous methods, in the proposed study, we first extract the first-order and second-order gradient information of low-light images and concatenate them with low-light images for multi-view feature analysis in the multi-view fusion encoder (MFE). Then, we suggest the multi-branch topology module (MTM) to fuse and decompose the multi-view features. Finally, we reconstruct the multi-view features through multi-view decomposition decoders (MDDs, including three sub-decoders) to generate potentially normal-light images. The first- and second-order gradient decoders will provide the enhancement decoder with multi-scale gradient prior features. Furthermore, we suggest a residual network to speed up network convergence while ensuring stable enhancement performance.We conduct experiments on widely adopted datasets. The results demonstrate the advantages of our method compared to other methods from both qualitative and quantitative perspectives. The source code is available at https://github.com/LouisYuxuLu/GPANet." @default.
- W4293498847 created "2022-08-29" @default.
- W4293498847 creator A5001514889 @default.
- W4293498847 creator A5015241563 @default.
- W4293498847 creator A5067730840 @default.
- W4293498847 creator A5074615062 @default.
- W4293498847 creator A5075642035 @default.
- W4293498847 date "2022-01-01" @default.
- W4293498847 modified "2023-10-10" @default.
- W4293498847 title "Low-Light Image Enhancement via Gradient Prior-Aided Network" @default.
- W4293498847 cites W1580436348 @default.
- W4293498847 cites W1976468890 @default.
- W4293498847 cites W1976478698 @default.
- W4293498847 cites W1986086122 @default.
- W4293498847 cites W1987444808 @default.
- W4293498847 cites W1995875735 @default.
- W4293498847 cites W2015196405 @default.
- W4293498847 cites W2054814429 @default.
- W4293498847 cites W2056370875 @default.
- W4293498847 cites W2057995993 @default.
- W4293498847 cites W2058333183 @default.
- W4293498847 cites W2061501622 @default.
- W4293498847 cites W2076205488 @default.
- W4293498847 cites W2083610878 @default.
- W4293498847 cites W2116973876 @default.
- W4293498847 cites W2121900453 @default.
- W4293498847 cites W2133665775 @default.
- W4293498847 cites W2139577851 @default.
- W4293498847 cites W2141983208 @default.
- W4293498847 cites W2147421915 @default.
- W4293498847 cites W2150461190 @default.
- W4293498847 cites W2150721269 @default.
- W4293498847 cites W2154549868 @default.
- W4293498847 cites W2164847484 @default.
- W4293498847 cites W2254039850 @default.
- W4293498847 cites W2296548841 @default.
- W4293498847 cites W2468596194 @default.
- W4293498847 cites W2566376500 @default.
- W4293498847 cites W2735974062 @default.
- W4293498847 cites W2766802800 @default.
- W4293498847 cites W2780108394 @default.
- W4293498847 cites W2783399029 @default.
- W4293498847 cites W2789454163 @default.
- W4293498847 cites W2791710889 @default.
- W4293498847 cites W2807563922 @default.
- W4293498847 cites W2919115771 @default.
- W4293498847 cites W2945180985 @default.
- W4293498847 cites W2948354154 @default.
- W4293498847 cites W2963766909 @default.
- W4293498847 cites W2981718299 @default.
- W4293498847 cites W2988734173 @default.
- W4293498847 cites W3015044426 @default.
- W4293498847 cites W3034598912 @default.
- W4293498847 cites W3035229960 @default.
- W4293498847 cites W3035731588 @default.
- W4293498847 cites W3042993386 @default.
- W4293498847 cites W3048737448 @default.
- W4293498847 cites W3107113662 @default.
- W4293498847 cites W3120540810 @default.
- W4293498847 cites W3121661546 @default.
- W4293498847 cites W3154123740 @default.
- W4293498847 cites W3161732772 @default.
- W4293498847 cites W3174792937 @default.
- W4293498847 cites W3175052667 @default.
- W4293498847 cites W3181175604 @default.
- W4293498847 cites W3182700213 @default.
- W4293498847 cites W3206130237 @default.
- W4293498847 cites W3207478457 @default.
- W4293498847 cites W4200292189 @default.
- W4293498847 cites W4206172195 @default.
- W4293498847 cites W4206993822 @default.
- W4293498847 cites W4220696844 @default.
- W4293498847 cites W4220824244 @default.
- W4293498847 cites W4281718770 @default.
- W4293498847 doi "https://doi.org/10.1109/access.2022.3202940" @default.
- W4293498847 hasPublicationYear "2022" @default.
- W4293498847 type Work @default.
- W4293498847 citedByCount "1" @default.
- W4293498847 countsByYear W42934988472023 @default.
- W4293498847 crossrefType "journal-article" @default.
- W4293498847 hasAuthorship W4293498847A5001514889 @default.
- W4293498847 hasAuthorship W4293498847A5015241563 @default.
- W4293498847 hasAuthorship W4293498847A5067730840 @default.
- W4293498847 hasAuthorship W4293498847A5074615062 @default.
- W4293498847 hasAuthorship W4293498847A5075642035 @default.
- W4293498847 hasBestOaLocation W42934988471 @default.
- W4293498847 hasConcept C106131492 @default.
- W4293498847 hasConcept C115961682 @default.
- W4293498847 hasConcept C119599485 @default.
- W4293498847 hasConcept C120665830 @default.
- W4293498847 hasConcept C121332964 @default.
- W4293498847 hasConcept C125245961 @default.
- W4293498847 hasConcept C127413603 @default.
- W4293498847 hasConcept C141353440 @default.
- W4293498847 hasConcept C153180895 @default.
- W4293498847 hasConcept C154945302 @default.
- W4293498847 hasConcept C182037307 @default.
- W4293498847 hasConcept C193536780 @default.