Matches in SemOpenAlex for { <https://semopenalex.org/work/W4313532008> ?p ?o ?g. }
- W4313532008 endingPage "2446" @default.
- W4313532008 startingPage "2437" @default.
- W4313532008 abstract "Previous single-image super-resolution methods assume that the blur kernel is known (e.g., bicubic) when degrading from high-resolution (HR) images to low-resolution (LR) images. They use a single degradation to train a model to restore HR images. However, the actual degradation in the real world is often unknown. It is difficult to deal with LR images caused by different degradations. To cope with the above situation, previous methods attempt to restore SR images using a blur kernel estimation structure that combines with a non-blind SR network. There are two problems that should be earnestly considered: (1) For accurate blur kernel estimation, insufficient correlation of consecutive kernels lead to an unsatisfied reconstruction result. (2) For ill-posed issue of image reconstruction, a more efficient constraint condition is worth trying. To solve the two problems, we propose an iterative dual regression network for an adaptive and precision blur kernel estimation, which improves the speed of kernel estimation by learning a dual mapping. Specifically, we design a Predictor-Generator structure: the Predictor, through several iterations, searching for accurate kernels through intermediate kernels and generated SR images; the Generator, generating final SR images with the help of the predicted kernels. More importantly, the elaborately designed dual learning strategy can not only provide additional constraints for accurate kernel estimation but also reduce the domain gap between SR images and HR images. Experiments on synthetic degraded images and real-world images show that our network is competitive in performance and superior in visual results." @default.
- W4313532008 created "2023-01-06" @default.
- W4313532008 creator A5024836695 @default.
- W4313532008 creator A5047734972 @default.
- W4313532008 creator A5049449184 @default.
- W4313532008 creator A5060431284 @default.
- W4313532008 creator A5077180419 @default.
- W4313532008 date "2023-01-03" @default.
- W4313532008 modified "2023-10-17" @default.
- W4313532008 title "Iterative dual regression network for blind image super-resolution" @default.
- W4313532008 cites W1791560514 @default.
- W4313532008 cites W1930824406 @default.
- W4313532008 cites W2047920195 @default.
- W4313532008 cites W2242218935 @default.
- W4313532008 cites W2503339013 @default.
- W4313532008 cites W2741137940 @default.
- W4313532008 cites W2780544323 @default.
- W4313532008 cites W2962793481 @default.
- W4313532008 cites W2962814024 @default.
- W4313532008 cites W2963372104 @default.
- W4313532008 cites W2963444790 @default.
- W4313532008 cites W2963470893 @default.
- W4313532008 cites W2963610452 @default.
- W4313532008 cites W2963704386 @default.
- W4313532008 cites W3026014384 @default.
- W4313532008 cites W3035302306 @default.
- W4313532008 cites W3035467803 @default.
- W4313532008 cites W3093778940 @default.
- W4313532008 cites W3099687741 @default.
- W4313532008 cites W3109552889 @default.
- W4313532008 cites W3134396242 @default.
- W4313532008 cites W3168684807 @default.
- W4313532008 cites W3174003276 @default.
- W4313532008 cites W3175727780 @default.
- W4313532008 cites W3175949974 @default.
- W4313532008 cites W3177381575 @default.
- W4313532008 cites W3180712890 @default.
- W4313532008 cites W3203631022 @default.
- W4313532008 cites W3204971388 @default.
- W4313532008 cites W3207918547 @default.
- W4313532008 cites W4285159007 @default.
- W4313532008 cites W54257720 @default.
- W4313532008 doi "https://doi.org/10.1007/s11760-022-02460-4" @default.
- W4313532008 hasPublicationYear "2023" @default.
- W4313532008 type Work @default.
- W4313532008 citedByCount "0" @default.
- W4313532008 crossrefType "journal-article" @default.
- W4313532008 hasAuthorship W4313532008A5024836695 @default.
- W4313532008 hasAuthorship W4313532008A5047734972 @default.
- W4313532008 hasAuthorship W4313532008A5049449184 @default.
- W4313532008 hasAuthorship W4313532008A5060431284 @default.
- W4313532008 hasAuthorship W4313532008A5077180419 @default.
- W4313532008 hasBestOaLocation W43135320082 @default.
- W4313532008 hasConcept C11413529 @default.
- W4313532008 hasConcept C114614502 @default.
- W4313532008 hasConcept C115961682 @default.
- W4313532008 hasConcept C121332964 @default.
- W4313532008 hasConcept C124952713 @default.
- W4313532008 hasConcept C142362112 @default.
- W4313532008 hasConcept C153180895 @default.
- W4313532008 hasConcept C154945302 @default.
- W4313532008 hasConcept C163258240 @default.
- W4313532008 hasConcept C171836373 @default.
- W4313532008 hasConcept C2524010 @default.
- W4313532008 hasConcept C2776036281 @default.
- W4313532008 hasConcept C2780980858 @default.
- W4313532008 hasConcept C2780992000 @default.
- W4313532008 hasConcept C31972630 @default.
- W4313532008 hasConcept C33923547 @default.
- W4313532008 hasConcept C41008148 @default.
- W4313532008 hasConcept C49608258 @default.
- W4313532008 hasConcept C62520636 @default.
- W4313532008 hasConcept C74193536 @default.
- W4313532008 hasConceptScore W4313532008C11413529 @default.
- W4313532008 hasConceptScore W4313532008C114614502 @default.
- W4313532008 hasConceptScore W4313532008C115961682 @default.
- W4313532008 hasConceptScore W4313532008C121332964 @default.
- W4313532008 hasConceptScore W4313532008C124952713 @default.
- W4313532008 hasConceptScore W4313532008C142362112 @default.
- W4313532008 hasConceptScore W4313532008C153180895 @default.
- W4313532008 hasConceptScore W4313532008C154945302 @default.
- W4313532008 hasConceptScore W4313532008C163258240 @default.
- W4313532008 hasConceptScore W4313532008C171836373 @default.
- W4313532008 hasConceptScore W4313532008C2524010 @default.
- W4313532008 hasConceptScore W4313532008C2776036281 @default.
- W4313532008 hasConceptScore W4313532008C2780980858 @default.
- W4313532008 hasConceptScore W4313532008C2780992000 @default.
- W4313532008 hasConceptScore W4313532008C31972630 @default.
- W4313532008 hasConceptScore W4313532008C33923547 @default.
- W4313532008 hasConceptScore W4313532008C41008148 @default.
- W4313532008 hasConceptScore W4313532008C49608258 @default.
- W4313532008 hasConceptScore W4313532008C62520636 @default.
- W4313532008 hasConceptScore W4313532008C74193536 @default.
- W4313532008 hasIssue "5" @default.
- W4313532008 hasLocation W43135320081 @default.
- W4313532008 hasLocation W43135320082 @default.
- W4313532008 hasOpenAccess W4313532008 @default.
- W4313532008 hasPrimaryLocation W43135320081 @default.