Matches in SemOpenAlex for { <https://semopenalex.org/work/W4384823360> ?p ?o ?g. }
Showing items 1 to 100 of
100
with 100 items per page.
- W4384823360 abstract "Deep learning can be used to achieve single-image superresolution (SR) reconstruction. To address problems encountered during this process, such as the number of network parameters, high training requirements on equipment performance, and inability to downsample certain SR images accurately, an image SR reconstruction algorithm based on deep residual network optimization is proposed. The model introduces wavelet transforms based on the original U-Net, where the U-Net is trained to obtain SR wavelet feature images at multiple scales simultaneously. This approach reduces the mapping space for the network to learn low- to high-resolution image mapping, which in turn reduces the training difficulty of the model. In terms of network details, the inverse wavelet transform is used in image upsampling to enhance the sparsity of the reconstruction layer in the original network. The network structure of the U-Net upsampling is adjusted slightly to enable the network to distinguish wavelet images from feature images, thereby improving the richness of the features extracted by the model. The experimental results show that the peak signal-to-noise ratio (PSNR) of the fourfold SR model is 32.35 and 28.68 on the Set5 and Set14 validation sets, respectively. Compared with networks that use wavelet prediction mechanisms, such as the deep wavelet prediction SR (DWSR) and deep wavelet prediction-based residual SR (DWRSR) models, the PSNR for all the tested public datasets is improved by 0.5. The method yields superior results in terms of both visual effect and PSNR, demonstrating the feasibility of the wavelet prediction mechanism in SR reconstruction and thus offering application value and research significance." @default.
- W4384823360 created "2023-07-21" @default.
- W4384823360 creator A5001165522 @default.
- W4384823360 creator A5002734812 @default.
- W4384823360 creator A5012682692 @default.
- W4384823360 creator A5030839263 @default.
- W4384823360 creator A5032414381 @default.
- W4384823360 creator A5047836896 @default.
- W4384823360 creator A5081017904 @default.
- W4384823360 date "2023-07-19" @default.
- W4384823360 modified "2023-09-28" @default.
- W4384823360 title "Improved wavelet prediction superresolution reconstruction based on U‐Net" @default.
- W4384823360 cites W1791560514 @default.
- W4384823360 cites W1930824406 @default.
- W4384823360 cites W2044451987 @default.
- W4384823360 cites W2047920195 @default.
- W4384823360 cites W2054515210 @default.
- W4384823360 cites W2085463895 @default.
- W4384823360 cites W2101946599 @default.
- W4384823360 cites W2110158442 @default.
- W4384823360 cites W2192954843 @default.
- W4384823360 cites W2194775991 @default.
- W4384823360 cites W2214802144 @default.
- W4384823360 cites W2242218935 @default.
- W4384823360 cites W2607041014 @default.
- W4384823360 cites W2741196023 @default.
- W4384823360 cites W2747898905 @default.
- W4384823360 cites W2866634454 @default.
- W4384823360 cites W2927933146 @default.
- W4384823360 cites W2963372104 @default.
- W4384823360 cites W3198884575 @default.
- W4384823360 cites W4296473473 @default.
- W4384823360 cites W4297095243 @default.
- W4384823360 cites W4309617247 @default.
- W4384823360 cites W4313555467 @default.
- W4384823360 cites W4319300887 @default.
- W4384823360 cites W54257720 @default.
- W4384823360 doi "https://doi.org/10.1049/ipr2.12878" @default.
- W4384823360 hasPublicationYear "2023" @default.
- W4384823360 type Work @default.
- W4384823360 citedByCount "0" @default.
- W4384823360 crossrefType "journal-article" @default.
- W4384823360 hasAuthorship W4384823360A5001165522 @default.
- W4384823360 hasAuthorship W4384823360A5002734812 @default.
- W4384823360 hasAuthorship W4384823360A5012682692 @default.
- W4384823360 hasAuthorship W4384823360A5030839263 @default.
- W4384823360 hasAuthorship W4384823360A5032414381 @default.
- W4384823360 hasAuthorship W4384823360A5047836896 @default.
- W4384823360 hasAuthorship W4384823360A5081017904 @default.
- W4384823360 hasBestOaLocation W43848233601 @default.
- W4384823360 hasConcept C110384440 @default.
- W4384823360 hasConcept C11413529 @default.
- W4384823360 hasConcept C115961682 @default.
- W4384823360 hasConcept C138885662 @default.
- W4384823360 hasConcept C141379421 @default.
- W4384823360 hasConcept C153180895 @default.
- W4384823360 hasConcept C154945302 @default.
- W4384823360 hasConcept C155512373 @default.
- W4384823360 hasConcept C155777637 @default.
- W4384823360 hasConcept C196216189 @default.
- W4384823360 hasConcept C2776401178 @default.
- W4384823360 hasConcept C41008148 @default.
- W4384823360 hasConcept C41895202 @default.
- W4384823360 hasConcept C46286280 @default.
- W4384823360 hasConcept C47432892 @default.
- W4384823360 hasConcept C73339587 @default.
- W4384823360 hasConcept C88829872 @default.
- W4384823360 hasConceptScore W4384823360C110384440 @default.
- W4384823360 hasConceptScore W4384823360C11413529 @default.
- W4384823360 hasConceptScore W4384823360C115961682 @default.
- W4384823360 hasConceptScore W4384823360C138885662 @default.
- W4384823360 hasConceptScore W4384823360C141379421 @default.
- W4384823360 hasConceptScore W4384823360C153180895 @default.
- W4384823360 hasConceptScore W4384823360C154945302 @default.
- W4384823360 hasConceptScore W4384823360C155512373 @default.
- W4384823360 hasConceptScore W4384823360C155777637 @default.
- W4384823360 hasConceptScore W4384823360C196216189 @default.
- W4384823360 hasConceptScore W4384823360C2776401178 @default.
- W4384823360 hasConceptScore W4384823360C41008148 @default.
- W4384823360 hasConceptScore W4384823360C41895202 @default.
- W4384823360 hasConceptScore W4384823360C46286280 @default.
- W4384823360 hasConceptScore W4384823360C47432892 @default.
- W4384823360 hasConceptScore W4384823360C73339587 @default.
- W4384823360 hasConceptScore W4384823360C88829872 @default.
- W4384823360 hasLocation W43848233601 @default.
- W4384823360 hasOpenAccess W4384823360 @default.
- W4384823360 hasPrimaryLocation W43848233601 @default.
- W4384823360 hasRelatedWork W1502966458 @default.
- W4384823360 hasRelatedWork W1997711983 @default.
- W4384823360 hasRelatedWork W2047056993 @default.
- W4384823360 hasRelatedWork W2084494395 @default.
- W4384823360 hasRelatedWork W2085792030 @default.
- W4384823360 hasRelatedWork W2103507103 @default.
- W4384823360 hasRelatedWork W2112061901 @default.
- W4384823360 hasRelatedWork W2151581766 @default.
- W4384823360 hasRelatedWork W2153999384 @default.
- W4384823360 hasRelatedWork W2390482320 @default.
- W4384823360 isParatext "false" @default.
- W4384823360 isRetracted "false" @default.
- W4384823360 workType "article" @default.