Matches in SemOpenAlex for { <https://semopenalex.org/work/W2896927224> ?p ?o ?g. }
- W2896927224 endingPage "1635" @default.
- W2896927224 startingPage "1625" @default.
- W2896927224 abstract "Dilated convolutions support expanding receptive field without parameter exploration or resolution loss, which turn out to be suitable for pixel-level prediction problems. In this paper, we propose multiscale single image super-resolution (SR) based on dilated convolutions. We adopt dilated convolutions to expand the receptive field size without incurring additional computational complexity. We mix standard convolutions and dilated convolutions in each layer, called mixed convolutions, i.e., in the mixed convolutional layer, and the feature extracted by dilated convolutions and standard convolutions are concatenated. We theoretically analyze the receptive field and intensity of mixed convolutions to discover their role in SR. Mixed convolutions remove blind spots and capture the correlation between low-resolution (LR) and high-resolution (HR) image pairs successfully, thus achieving good generalization ability. We verify those properties of mixed convolutions by training 5-layer and 10-layer networks. We also train a 20-layer deep network to compare the performance of the proposed method with those of the state-of-the-art ones. Moreover, we jointly learn maps with different scales from a LR image to its HR one in a single network. Experimental results demonstrate that the proposed method outperforms the state-of-the-art ones in terms of PSNR and SSIM, especially for a large-scale factor." @default.
- W2896927224 created "2018-10-26" @default.
- W2896927224 creator A5003623628 @default.
- W2896927224 creator A5061972088 @default.
- W2896927224 creator A5088335237 @default.
- W2896927224 date "2019-04-01" @default.
- W2896927224 modified "2023-10-10" @default.
- W2896927224 title "DCSR: Dilated Convolutions for Single Image Super-Resolution" @default.
- W2896927224 cites W1677182931 @default.
- W2896927224 cites W1885185971 @default.
- W2896927224 cites W1930824406 @default.
- W2896927224 cites W1949096787 @default.
- W2896927224 cites W1950594372 @default.
- W2896927224 cites W2010070459 @default.
- W2896927224 cites W2047920195 @default.
- W2896927224 cites W2088254198 @default.
- W2896927224 cites W2118963448 @default.
- W2896927224 cites W2121058967 @default.
- W2896927224 cites W2121927366 @default.
- W2896927224 cites W2149669120 @default.
- W2896927224 cites W2150081556 @default.
- W2896927224 cites W2164551808 @default.
- W2896927224 cites W2214802144 @default.
- W2896927224 cites W2242218935 @default.
- W2896927224 cites W2476548250 @default.
- W2896927224 cites W2739757502 @default.
- W2896927224 cites W2919115771 @default.
- W2896927224 cites W2963372104 @default.
- W2896927224 doi "https://doi.org/10.1109/tip.2018.2877483" @default.
- W2896927224 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/30346286" @default.
- W2896927224 hasPublicationYear "2019" @default.
- W2896927224 type Work @default.
- W2896927224 sameAs 2896927224 @default.
- W2896927224 citedByCount "103" @default.
- W2896927224 countsByYear W28969272242019 @default.
- W2896927224 countsByYear W28969272242020 @default.
- W2896927224 countsByYear W28969272242021 @default.
- W2896927224 countsByYear W28969272242022 @default.
- W2896927224 countsByYear W28969272242023 @default.
- W2896927224 crossrefType "journal-article" @default.
- W2896927224 hasAuthorship W2896927224A5003623628 @default.
- W2896927224 hasAuthorship W2896927224A5061972088 @default.
- W2896927224 hasAuthorship W2896927224A5088335237 @default.
- W2896927224 hasConcept C11413529 @default.
- W2896927224 hasConcept C115961682 @default.
- W2896927224 hasConcept C134306372 @default.
- W2896927224 hasConcept C138268822 @default.
- W2896927224 hasConcept C138885662 @default.
- W2896927224 hasConcept C153180895 @default.
- W2896927224 hasConcept C154945302 @default.
- W2896927224 hasConcept C160633673 @default.
- W2896927224 hasConcept C177148314 @default.
- W2896927224 hasConcept C179799912 @default.
- W2896927224 hasConcept C205372480 @default.
- W2896927224 hasConcept C2776401178 @default.
- W2896927224 hasConcept C33923547 @default.
- W2896927224 hasConcept C41008148 @default.
- W2896927224 hasConcept C41895202 @default.
- W2896927224 hasConcept C45347329 @default.
- W2896927224 hasConcept C50644808 @default.
- W2896927224 hasConcept C81363708 @default.
- W2896927224 hasConceptScore W2896927224C11413529 @default.
- W2896927224 hasConceptScore W2896927224C115961682 @default.
- W2896927224 hasConceptScore W2896927224C134306372 @default.
- W2896927224 hasConceptScore W2896927224C138268822 @default.
- W2896927224 hasConceptScore W2896927224C138885662 @default.
- W2896927224 hasConceptScore W2896927224C153180895 @default.
- W2896927224 hasConceptScore W2896927224C154945302 @default.
- W2896927224 hasConceptScore W2896927224C160633673 @default.
- W2896927224 hasConceptScore W2896927224C177148314 @default.
- W2896927224 hasConceptScore W2896927224C179799912 @default.
- W2896927224 hasConceptScore W2896927224C205372480 @default.
- W2896927224 hasConceptScore W2896927224C2776401178 @default.
- W2896927224 hasConceptScore W2896927224C33923547 @default.
- W2896927224 hasConceptScore W2896927224C41008148 @default.
- W2896927224 hasConceptScore W2896927224C41895202 @default.
- W2896927224 hasConceptScore W2896927224C45347329 @default.
- W2896927224 hasConceptScore W2896927224C50644808 @default.
- W2896927224 hasConceptScore W2896927224C81363708 @default.
- W2896927224 hasFunder F4320321001 @default.
- W2896927224 hasIssue "4" @default.
- W2896927224 hasLocation W28969272241 @default.
- W2896927224 hasLocation W28969272242 @default.
- W2896927224 hasOpenAccess W2896927224 @default.
- W2896927224 hasPrimaryLocation W28969272241 @default.
- W2896927224 hasRelatedWork W2295021132 @default.
- W2896927224 hasRelatedWork W2565951482 @default.
- W2896927224 hasRelatedWork W2576269910 @default.
- W2896927224 hasRelatedWork W2760085659 @default.
- W2896927224 hasRelatedWork W2810384904 @default.
- W2896927224 hasRelatedWork W2969396093 @default.
- W2896927224 hasRelatedWork W3013138473 @default.
- W2896927224 hasRelatedWork W3106036237 @default.
- W2896927224 hasRelatedWork W3176001077 @default.
- W2896927224 hasRelatedWork W3200375696 @default.
- W2896927224 hasVolume "28" @default.
- W2896927224 isParatext "false" @default.
- W2896927224 isRetracted "false" @default.