Matches in SemOpenAlex for { <https://semopenalex.org/work/W4382246298> ?p ?o ?g. }
Showing items 1 to 82 of
82
with 100 items per page.
- W4382246298 abstract "The visual quality of nighttime photographs diminishes greatly due to low contrast and high noise. We need a robust image enhancement methodology to improve such low-light images close to standard daylight images. Due to deteriorated conditions of uneven light and noise, this image enhancement problem becomes ill-posed. Our paper has proposed a Densely Residual Attention Network (DRANet), an end-to-end attention base densely residual network. The architecture of DRANet consists of sub-modules convolution block (CB) and densely residual feature - convolutional block attention module (DRF-CBAM). DFR-CBAM also has sub-modules, deep residual feature block (DRFB), and convolutional block attention module (CBAM). Using the most recent results from attention and deep residual-based convolution networks in number of computer vision problems, we have used DRFB to enhance the features in-depth by using its dense and residual skip connections. Similarly, features in both spatial and channel axis have been extracted by using a lightweight CBAM attention module. Contrast, luminosity, and noise of the enhanced images have been balanced by additionally implementing a color balancing function at the end of the proposed network. Furthermore, we have used a combination of <i>L<sub>Lab</sub></i>, <i>L<sub>SSIM</sub></i> and <i>L<sub>MAE</sub></i> loss functions to make the proposed network stable and recover both contextual and local details while training. MAE, PSNR, SSIM, MS-SSIM, FSIM, Cosine Similarity, and deltaE2000 have been used as referenced while NIQE as nonreferenced based image quality assessment (IQA) metric. Experiment results showed that our proposed methodology is very effective with higher referenced and lower non-referenced image IQA metrics values. Furthermore, the effectiveness of our method has also demonstrated by the visual and perceptual quality of enhanced images." @default.
- W4382246298 created "2023-06-28" @default.
- W4382246298 creator A5009407457 @default.
- W4382246298 creator A5012786887 @default.
- W4382246298 creator A5019618306 @default.
- W4382246298 creator A5041583325 @default.
- W4382246298 creator A5067972997 @default.
- W4382246298 creator A5069882431 @default.
- W4382246298 creator A5089032960 @default.
- W4382246298 date "2023-06-27" @default.
- W4382246298 modified "2023-09-30" @default.
- W4382246298 title "DRA-Net: densely residual attention based low-light image enhancement" @default.
- W4382246298 doi "https://doi.org/10.1117/12.2680479" @default.
- W4382246298 hasPublicationYear "2023" @default.
- W4382246298 type Work @default.
- W4382246298 citedByCount "0" @default.
- W4382246298 crossrefType "proceedings-article" @default.
- W4382246298 hasAuthorship W4382246298A5009407457 @default.
- W4382246298 hasAuthorship W4382246298A5012786887 @default.
- W4382246298 hasAuthorship W4382246298A5019618306 @default.
- W4382246298 hasAuthorship W4382246298A5041583325 @default.
- W4382246298 hasAuthorship W4382246298A5067972997 @default.
- W4382246298 hasAuthorship W4382246298A5069882431 @default.
- W4382246298 hasAuthorship W4382246298A5089032960 @default.
- W4382246298 hasConcept C11413529 @default.
- W4382246298 hasConcept C115961682 @default.
- W4382246298 hasConcept C127413603 @default.
- W4382246298 hasConcept C138885662 @default.
- W4382246298 hasConcept C153180895 @default.
- W4382246298 hasConcept C154945302 @default.
- W4382246298 hasConcept C155512373 @default.
- W4382246298 hasConcept C176217482 @default.
- W4382246298 hasConcept C21547014 @default.
- W4382246298 hasConcept C2524010 @default.
- W4382246298 hasConcept C2776401178 @default.
- W4382246298 hasConcept C2777210771 @default.
- W4382246298 hasConcept C31972630 @default.
- W4382246298 hasConcept C33923547 @default.
- W4382246298 hasConcept C41008148 @default.
- W4382246298 hasConcept C41895202 @default.
- W4382246298 hasConcept C45347329 @default.
- W4382246298 hasConcept C50644808 @default.
- W4382246298 hasConcept C55020928 @default.
- W4382246298 hasConcept C81363708 @default.
- W4382246298 hasConcept C99498987 @default.
- W4382246298 hasConceptScore W4382246298C11413529 @default.
- W4382246298 hasConceptScore W4382246298C115961682 @default.
- W4382246298 hasConceptScore W4382246298C127413603 @default.
- W4382246298 hasConceptScore W4382246298C138885662 @default.
- W4382246298 hasConceptScore W4382246298C153180895 @default.
- W4382246298 hasConceptScore W4382246298C154945302 @default.
- W4382246298 hasConceptScore W4382246298C155512373 @default.
- W4382246298 hasConceptScore W4382246298C176217482 @default.
- W4382246298 hasConceptScore W4382246298C21547014 @default.
- W4382246298 hasConceptScore W4382246298C2524010 @default.
- W4382246298 hasConceptScore W4382246298C2776401178 @default.
- W4382246298 hasConceptScore W4382246298C2777210771 @default.
- W4382246298 hasConceptScore W4382246298C31972630 @default.
- W4382246298 hasConceptScore W4382246298C33923547 @default.
- W4382246298 hasConceptScore W4382246298C41008148 @default.
- W4382246298 hasConceptScore W4382246298C41895202 @default.
- W4382246298 hasConceptScore W4382246298C45347329 @default.
- W4382246298 hasConceptScore W4382246298C50644808 @default.
- W4382246298 hasConceptScore W4382246298C55020928 @default.
- W4382246298 hasConceptScore W4382246298C81363708 @default.
- W4382246298 hasConceptScore W4382246298C99498987 @default.
- W4382246298 hasLocation W43822462981 @default.
- W4382246298 hasOpenAccess W4382246298 @default.
- W4382246298 hasPrimaryLocation W43822462981 @default.
- W4382246298 hasRelatedWork W2295021132 @default.
- W4382246298 hasRelatedWork W2760085659 @default.
- W4382246298 hasRelatedWork W2788343277 @default.
- W4382246298 hasRelatedWork W2798617638 @default.
- W4382246298 hasRelatedWork W2929240682 @default.
- W4382246298 hasRelatedWork W2961623865 @default.
- W4382246298 hasRelatedWork W3044388927 @default.
- W4382246298 hasRelatedWork W3106036237 @default.
- W4382246298 hasRelatedWork W3133981001 @default.
- W4382246298 hasRelatedWork W4283204632 @default.
- W4382246298 isParatext "false" @default.
- W4382246298 isRetracted "false" @default.
- W4382246298 workType "article" @default.