Matches in SemOpenAlex for { <https://semopenalex.org/work/W4283528430> ?p ?o ?g. }
- W4283528430 endingPage "3393" @default.
- W4283528430 startingPage "3374" @default.
- W4283528430 abstract "In realistic low-light environments, images captured by imaging devices often have problems such as low brightness and low contrast, serious loss of detail information, and a large amount of noise, posing major challenges to computer vision tasks. Low-light image enhancement can effectively improve the overall quality of the image, which has important significance and application value. In this study, an attention-based multi-channel feature fusion enhancement network (M-FFENet) is proposed to process low-light images. In this network, a feature extraction model is first used to obtain the deep features of the downsampled low-light images and fit them to an affine bilateral grid. Second, the addition of attention-based residual dense blocks (ARDB) allows the network to focus on more details and spatial information. Meanwhile, all color channels are considered. The channel features and bilateral meshes are then linearly interpolated using the feature reconfiguration model (FRM) to obtain high-quality features containing rich color and texture information. Next, the feature fusion module (FFM) is used to fuse features that contain different information. Enhancement model is used to further recover texture and detail in the image. Finally, the enhanced image is output. Numerous experimental results have shown that the method achieves better results in both quantitative and qualitative aspects compared to other methods." @default.
- W4283528430 created "2022-06-27" @default.
- W4283528430 creator A5000298140 @default.
- W4283528430 creator A5017658514 @default.
- W4283528430 creator A5028836596 @default.
- W4283528430 creator A5078116487 @default.
- W4283528430 date "2022-06-25" @default.
- W4283528430 modified "2023-10-15" @default.
- W4283528430 title "Attention‐based multi‐channel feature fusion enhancement network to process low‐light images" @default.
- W4283528430 cites W1580436348 @default.
- W4283528430 cites W1976468890 @default.
- W4283528430 cites W1977725648 @default.
- W4283528430 cites W1982471090 @default.
- W4283528430 cites W1987444808 @default.
- W4283528430 cites W2054814429 @default.
- W4283528430 cites W2102166818 @default.
- W4283528430 cites W2121900453 @default.
- W4283528430 cites W2133665775 @default.
- W4283528430 cites W2141125852 @default.
- W4283528430 cites W2141983208 @default.
- W4283528430 cites W2150721269 @default.
- W4283528430 cites W2194011657 @default.
- W4283528430 cites W2194775991 @default.
- W4283528430 cites W2296548841 @default.
- W4283528430 cites W2566376500 @default.
- W4283528430 cites W2610602405 @default.
- W4283528430 cites W2752782242 @default.
- W4283528430 cites W2780534582 @default.
- W4283528430 cites W2798844427 @default.
- W4283528430 cites W2895382611 @default.
- W4283528430 cites W2945180985 @default.
- W4283528430 cites W2947137735 @default.
- W4283528430 cites W2955813853 @default.
- W4283528430 cites W2955889502 @default.
- W4283528430 cites W2963458902 @default.
- W4283528430 cites W2981718299 @default.
- W4283528430 cites W2995081268 @default.
- W4283528430 cites W3003838261 @default.
- W4283528430 cites W3015044426 @default.
- W4283528430 cites W3016917677 @default.
- W4283528430 cites W3032766569 @default.
- W4283528430 cites W3034347506 @default.
- W4283528430 cites W3034660707 @default.
- W4283528430 cites W3035104062 @default.
- W4283528430 cites W3035326127 @default.
- W4283528430 cites W3035731588 @default.
- W4283528430 cites W3038988252 @default.
- W4283528430 cites W3042993386 @default.
- W4283528430 cites W3094458433 @default.
- W4283528430 cites W3106758205 @default.
- W4283528430 cites W3107113662 @default.
- W4283528430 cites W3119456559 @default.
- W4283528430 cites W3121661546 @default.
- W4283528430 cites W3124399606 @default.
- W4283528430 cites W3149802657 @default.
- W4283528430 cites W3174792937 @default.
- W4283528430 cites W4207024994 @default.
- W4283528430 cites W4210734798 @default.
- W4283528430 cites W4214862086 @default.
- W4283528430 cites W4226213342 @default.
- W4283528430 cites W4226245048 @default.
- W4283528430 doi "https://doi.org/10.1049/ipr2.12571" @default.
- W4283528430 hasPublicationYear "2022" @default.
- W4283528430 type Work @default.
- W4283528430 citedByCount "0" @default.
- W4283528430 crossrefType "journal-article" @default.
- W4283528430 hasAuthorship W4283528430A5000298140 @default.
- W4283528430 hasAuthorship W4283528430A5017658514 @default.
- W4283528430 hasAuthorship W4283528430A5028836596 @default.
- W4283528430 hasAuthorship W4283528430A5078116487 @default.
- W4283528430 hasBestOaLocation W42835284301 @default.
- W4283528430 hasConcept C111919701 @default.
- W4283528430 hasConcept C115961682 @default.
- W4283528430 hasConcept C119599485 @default.
- W4283528430 hasConcept C120665830 @default.
- W4283528430 hasConcept C121332964 @default.
- W4283528430 hasConcept C125245961 @default.
- W4283528430 hasConcept C127162648 @default.
- W4283528430 hasConcept C127413603 @default.
- W4283528430 hasConcept C138885662 @default.
- W4283528430 hasConcept C141353440 @default.
- W4283528430 hasConcept C153180895 @default.
- W4283528430 hasConcept C154945302 @default.
- W4283528430 hasConcept C192209626 @default.
- W4283528430 hasConcept C202444582 @default.
- W4283528430 hasConcept C2776401178 @default.
- W4283528430 hasConcept C31258907 @default.
- W4283528430 hasConcept C31972630 @default.
- W4283528430 hasConcept C33923547 @default.
- W4283528430 hasConcept C41008148 @default.
- W4283528430 hasConcept C41895202 @default.
- W4283528430 hasConcept C52622490 @default.
- W4283528430 hasConcept C69744172 @default.
- W4283528430 hasConcept C92757383 @default.
- W4283528430 hasConcept C98045186 @default.
- W4283528430 hasConceptScore W4283528430C111919701 @default.
- W4283528430 hasConceptScore W4283528430C115961682 @default.
- W4283528430 hasConceptScore W4283528430C119599485 @default.