Matches in SemOpenAlex for { <https://semopenalex.org/work/W4313646834> ?p ?o ?g. }
- W4313646834 endingPage "33" @default.
- W4313646834 startingPage "33" @default.
- W4313646834 abstract "Deep convolutional neural networks (DCNNs) have manifested significant performance gains for single-image super-resolution (SISR) in the past few years. Most of the existing methods are generally implemented in a fully supervised way using large-scale training samples and only learn the SR models restricted to specific data. Thus, the adaptation of these models to real low-resolution (LR) images captured under uncontrolled imaging conditions usually leads to poor SR results. This study proposes a zero-shot blind SR framework via leveraging the power of deep learning, but without the requirement of the prior training using predefined imaged samples. It is well known that there are two unknown data: the underlying target high-resolution (HR) images and the degradation operations in the imaging procedure hidden in the observed LR images. Taking these in mind, we specifically employed two deep networks for respectively modeling the priors of both the target HR image and its corresponding degradation kernel and designed a degradation block to realize the observation procedure of the LR image. Via formulating the loss function as the approximation error of the observed LR image, we established a completely blind end-to-end zero-shot learning framework for simultaneously predicting the target HR image and the degradation kernel without any external data. In particular, we adopted a multi-scale encoder–decoder subnet to serve as the image prior learning network, a simple fully connected subnet to serve as the kernel prior learning network, and a specific depthwise convolutional block to implement the degradation procedure. We conducted extensive experiments on several benchmark datasets and manifested the great superiority and high generalization of our method over both SOTA supervised and unsupervised SR methods." @default.
- W4313646834 created "2023-01-07" @default.
- W4313646834 creator A5014430005 @default.
- W4313646834 creator A5086851360 @default.
- W4313646834 date "2023-01-05" @default.
- W4313646834 modified "2023-09-26" @default.
- W4313646834 title "Zero-Shot Blind Learning for Single-Image Super-Resolution" @default.
- W4313646834 cites W1540764732 @default.
- W4313646834 cites W1885185971 @default.
- W4313646834 cites W2047920195 @default.
- W4313646834 cites W2194775991 @default.
- W4313646834 cites W2214802144 @default.
- W4313646834 cites W2242218935 @default.
- W4313646834 cites W2476548250 @default.
- W4313646834 cites W2607041014 @default.
- W4313646834 cites W2883102461 @default.
- W4313646834 cites W2891158090 @default.
- W4313646834 cites W2962770929 @default.
- W4313646834 cites W2962793481 @default.
- W4313646834 cites W2962814024 @default.
- W4313646834 cites W2962903125 @default.
- W4313646834 cites W2963037581 @default.
- W4313646834 cites W2963073614 @default.
- W4313646834 cites W2963372104 @default.
- W4313646834 cites W2963444790 @default.
- W4313646834 cites W2963470893 @default.
- W4313646834 cites W2963704386 @default.
- W4313646834 cites W2963774720 @default.
- W4313646834 cites W2963800363 @default.
- W4313646834 cites W2964277374 @default.
- W4313646834 cites W2987150909 @default.
- W4313646834 cites W3011043518 @default.
- W4313646834 cites W3011456574 @default.
- W4313646834 cites W3012322483 @default.
- W4313646834 cites W3035190116 @default.
- W4313646834 cites W3035304632 @default.
- W4313646834 cites W3196260040 @default.
- W4313646834 doi "https://doi.org/10.3390/info14010033" @default.
- W4313646834 hasPublicationYear "2023" @default.
- W4313646834 type Work @default.
- W4313646834 citedByCount "0" @default.
- W4313646834 crossrefType "journal-article" @default.
- W4313646834 hasAuthorship W4313646834A5014430005 @default.
- W4313646834 hasAuthorship W4313646834A5086851360 @default.
- W4313646834 hasBestOaLocation W43136468341 @default.
- W4313646834 hasConcept C107673813 @default.
- W4313646834 hasConcept C108583219 @default.
- W4313646834 hasConcept C114614502 @default.
- W4313646834 hasConcept C115961682 @default.
- W4313646834 hasConcept C153180895 @default.
- W4313646834 hasConcept C154945302 @default.
- W4313646834 hasConcept C177769412 @default.
- W4313646834 hasConcept C21099817 @default.
- W4313646834 hasConcept C2524010 @default.
- W4313646834 hasConcept C2776214188 @default.
- W4313646834 hasConcept C2777210771 @default.
- W4313646834 hasConcept C31258907 @default.
- W4313646834 hasConcept C31972630 @default.
- W4313646834 hasConcept C33923547 @default.
- W4313646834 hasConcept C41008148 @default.
- W4313646834 hasConcept C74193536 @default.
- W4313646834 hasConcept C81363708 @default.
- W4313646834 hasConceptScore W4313646834C107673813 @default.
- W4313646834 hasConceptScore W4313646834C108583219 @default.
- W4313646834 hasConceptScore W4313646834C114614502 @default.
- W4313646834 hasConceptScore W4313646834C115961682 @default.
- W4313646834 hasConceptScore W4313646834C153180895 @default.
- W4313646834 hasConceptScore W4313646834C154945302 @default.
- W4313646834 hasConceptScore W4313646834C177769412 @default.
- W4313646834 hasConceptScore W4313646834C21099817 @default.
- W4313646834 hasConceptScore W4313646834C2524010 @default.
- W4313646834 hasConceptScore W4313646834C2776214188 @default.
- W4313646834 hasConceptScore W4313646834C2777210771 @default.
- W4313646834 hasConceptScore W4313646834C31258907 @default.
- W4313646834 hasConceptScore W4313646834C31972630 @default.
- W4313646834 hasConceptScore W4313646834C33923547 @default.
- W4313646834 hasConceptScore W4313646834C41008148 @default.
- W4313646834 hasConceptScore W4313646834C74193536 @default.
- W4313646834 hasConceptScore W4313646834C81363708 @default.
- W4313646834 hasFunder F4320320912 @default.
- W4313646834 hasFunder F4320334764 @default.
- W4313646834 hasIssue "1" @default.
- W4313646834 hasLocation W43136468341 @default.
- W4313646834 hasOpenAccess W4313646834 @default.
- W4313646834 hasPrimaryLocation W43136468341 @default.
- W4313646834 hasRelatedWork W2731899572 @default.
- W4313646834 hasRelatedWork W2999805992 @default.
- W4313646834 hasRelatedWork W3011074480 @default.
- W4313646834 hasRelatedWork W3116150086 @default.
- W4313646834 hasRelatedWork W3133861977 @default.
- W4313646834 hasRelatedWork W3192840557 @default.
- W4313646834 hasRelatedWork W4200173597 @default.
- W4313646834 hasRelatedWork W4291897433 @default.
- W4313646834 hasRelatedWork W4312417841 @default.
- W4313646834 hasRelatedWork W4321369474 @default.
- W4313646834 hasVolume "14" @default.
- W4313646834 isParatext "false" @default.
- W4313646834 isRetracted "false" @default.