Matches in SemOpenAlex for { <https://semopenalex.org/work/W2599698286> ?p ?o ?g. }
- W2599698286 endingPage "1717" @default.
- W2599698286 startingPage "1702" @default.
- W2599698286 abstract "Single image super-resolution (SISR) is a challenging work, which aims to recover the missing information in an observed low-resolution (LR) image and generate the corresponding high-resolution (HR) version. As the SISR problem is severely ill-conditioned, effective prior knowledge of HR images is necessary to well pose the HR estimation. In this paper, an effective SISR method is proposed via the local structure-adaptive transform-based nonlocal self-similarity modeling and learning-based gradient regularization (LSNSGR). The LSNSGR exploits both the natural and learned priors of HR images, thus integrating the merits of conventional reconstruction-based and learning-based SISR algorithms. More specifically, on the one hand, we characterize nonlocal self-similarity prior (natural prior) in transform domain by using the designed local structure-adaptive transform; on the other hand, the gradient prior (learned prior) is learned via the jointly optimized regression model. The former prior is effective in suppressing visual artifacts, while the latter performs well in recovering sharp edges and fine structures. By incorporating the two complementary priors into the maximum a posteriori-based reconstruction framework, we optimize a hybrid L1- and L2-regularized minimization problem to achieve an estimation of the desired HR image. Extensive experimental results suggest that the proposed LSNSGR produces better HR estimations than many state-of-the-art works in terms of both perceptual and quantitative evaluations." @default.
- W2599698286 created "2017-04-07" @default.
- W2599698286 creator A5021067690 @default.
- W2599698286 creator A5029742741 @default.
- W2599698286 creator A5039718733 @default.
- W2599698286 creator A5059067107 @default.
- W2599698286 date "2017-08-01" @default.
- W2599698286 modified "2023-09-30" @default.
- W2599698286 title "Single Image Super-Resolution via Adaptive Transform-Based Nonlocal Self-Similarity Modeling and Learning-Based Gradient Regularization" @default.
- W2599698286 cites W1508652512 @default.
- W2599698286 cites W1721184332 @default.
- W2599698286 cites W1885185971 @default.
- W2599698286 cites W1930824406 @default.
- W2599698286 cites W1949096787 @default.
- W2599698286 cites W1971066121 @default.
- W2599698286 cites W1978749115 @default.
- W2599698286 cites W1992408872 @default.
- W2599698286 cites W1995228944 @default.
- W2599698286 cites W1999174140 @default.
- W2599698286 cites W2006262236 @default.
- W2599698286 cites W2011952414 @default.
- W2599698286 cites W2015374556 @default.
- W2599698286 cites W2027755635 @default.
- W2599698286 cites W2028790650 @default.
- W2599698286 cites W2029684123 @default.
- W2599698286 cites W2033673394 @default.
- W2599698286 cites W2038323587 @default.
- W2599698286 cites W2042984553 @default.
- W2599698286 cites W2047920195 @default.
- W2599698286 cites W2056370875 @default.
- W2599698286 cites W2057065563 @default.
- W2599698286 cites W2062820291 @default.
- W2599698286 cites W2078008442 @default.
- W2599698286 cites W2080875060 @default.
- W2599698286 cites W2085692415 @default.
- W2599698286 cites W2087436818 @default.
- W2599698286 cites W2097074225 @default.
- W2599698286 cites W2097200430 @default.
- W2599698286 cites W2103844245 @default.
- W2599698286 cites W2111454493 @default.
- W2599698286 cites W2118963448 @default.
- W2599698286 cites W2121058967 @default.
- W2599698286 cites W2124378283 @default.
- W2599698286 cites W2130638881 @default.
- W2599698286 cites W2131024476 @default.
- W2599698286 cites W2133665775 @default.
- W2599698286 cites W2137974653 @default.
- W2599698286 cites W2138863404 @default.
- W2599698286 cites W2140050933 @default.
- W2599698286 cites W2142058898 @default.
- W2599698286 cites W2142884912 @default.
- W2599698286 cites W2150081556 @default.
- W2599698286 cites W2157190232 @default.
- W2599698286 cites W2172128189 @default.
- W2599698286 cites W2184334976 @default.
- W2599698286 cites W2187133255 @default.
- W2599698286 cites W2214802144 @default.
- W2599698286 cites W2242218935 @default.
- W2599698286 cites W2284619914 @default.
- W2599698286 cites W2290061803 @default.
- W2599698286 cites W2290736026 @default.
- W2599698286 cites W2331619054 @default.
- W2599698286 cites W2345557152 @default.
- W2599698286 cites W236254921 @default.
- W2599698286 cites W2461349148 @default.
- W2599698286 cites W2509348655 @default.
- W2599698286 cites W2518224564 @default.
- W2599698286 cites W2518227085 @default.
- W2599698286 cites W2527019762 @default.
- W2599698286 cites W3104720471 @default.
- W2599698286 doi "https://doi.org/10.1109/tmm.2017.2688920" @default.
- W2599698286 hasPublicationYear "2017" @default.
- W2599698286 type Work @default.
- W2599698286 sameAs 2599698286 @default.
- W2599698286 citedByCount "42" @default.
- W2599698286 countsByYear W25996982862017 @default.
- W2599698286 countsByYear W25996982862018 @default.
- W2599698286 countsByYear W25996982862019 @default.
- W2599698286 countsByYear W25996982862020 @default.
- W2599698286 countsByYear W25996982862021 @default.
- W2599698286 countsByYear W25996982862022 @default.
- W2599698286 countsByYear W25996982862023 @default.
- W2599698286 crossrefType "journal-article" @default.
- W2599698286 hasAuthorship W2599698286A5021067690 @default.
- W2599698286 hasAuthorship W2599698286A5029742741 @default.
- W2599698286 hasAuthorship W2599698286A5039718733 @default.
- W2599698286 hasAuthorship W2599698286A5059067107 @default.
- W2599698286 hasConcept C103278499 @default.
- W2599698286 hasConcept C105795698 @default.
- W2599698286 hasConcept C107673813 @default.
- W2599698286 hasConcept C111472728 @default.
- W2599698286 hasConcept C115961682 @default.
- W2599698286 hasConcept C138885662 @default.
- W2599698286 hasConcept C141239990 @default.
- W2599698286 hasConcept C141379421 @default.
- W2599698286 hasConcept C153180895 @default.
- W2599698286 hasConcept C154945302 @default.
- W2599698286 hasConcept C177769412 @default.