Matches in SemOpenAlex for { <https://semopenalex.org/work/W4387056622> ?p ?o ?g. }
Showing items 1 to 85 of
85
with 100 items per page.
- W4387056622 endingPage "121748" @default.
- W4387056622 startingPage "121748" @default.
- W4387056622 abstract "Blind super-resolution endeavors to restore clear and high-resolution images from obscure degraded images. To comprehensively encompass the diverse range of real image degradations, prevailing research methods either explicitly or implicitly simulate image degradation. Nevertheless, a majority of prior approaches employ conventional interpolation algorithms for resize operations, thereby impeding the breadth of image degradation diversity. In the case of implicit models, we propose a dynamic learnable degradation (DLD) model, achieved through self-supervised training. This model leverages a dynamic downsampling module to generate a multitude of low-resolution images. By introducing DLD as a novel downsampling method, we devise an original explicit degradation model, which generates additional sets of training image pairs to enhance the practical restoration outcomes of ESRGAN for natural images, called Dynamic-ESRGAN. We also account for the overall degradation and put forth a hybrid-order degradation model to encompass the manifold degradations prevalent in natural images. Exhaustive experimental comparisons conducted on both synthetic and real datasets have unequivocally demonstrated the significant advantages of our DLD and Dynamic-ESRGAN models, both in terms of objective indicators and subjective perception." @default.
- W4387056622 created "2023-09-27" @default.
- W4387056622 creator A5020084530 @default.
- W4387056622 creator A5037098300 @default.
- W4387056622 creator A5039417073 @default.
- W4387056622 creator A5046527432 @default.
- W4387056622 date "2024-03-01" @default.
- W4387056622 modified "2023-10-06" @default.
- W4387056622 title "Dynamic Learnable Degradation for Blind Super-Resolution" @default.
- W4387056622 cites W1885185971 @default.
- W4387056622 cites W2607202125 @default.
- W4387056622 cites W2741137940 @default.
- W4387056622 cites W2866634454 @default.
- W4387056622 cites W2883102461 @default.
- W4387056622 cites W2932253358 @default.
- W4387056622 cites W2954930822 @default.
- W4387056622 cites W2962814024 @default.
- W4387056622 cites W2963372104 @default.
- W4387056622 cites W2963729050 @default.
- W4387056622 cites W2971292464 @default.
- W4387056622 cites W3011456574 @default.
- W4387056622 cites W3034247386 @default.
- W4387056622 cites W3034259513 @default.
- W4387056622 cites W3034785019 @default.
- W4387056622 cites W3035190116 @default.
- W4387056622 cites W3176334871 @default.
- W4387056622 cites W3176997885 @default.
- W4387056622 cites W3179253672 @default.
- W4387056622 cites W3195587117 @default.
- W4387056622 cites W4221153217 @default.
- W4387056622 cites W4231167724 @default.
- W4387056622 cites W4280605878 @default.
- W4387056622 cites W4297497086 @default.
- W4387056622 cites W4312763936 @default.
- W4387056622 doi "https://doi.org/10.1016/j.eswa.2023.121748" @default.
- W4387056622 hasPublicationYear "2024" @default.
- W4387056622 type Work @default.
- W4387056622 citedByCount "0" @default.
- W4387056622 crossrefType "journal-article" @default.
- W4387056622 hasAuthorship W4387056622A5020084530 @default.
- W4387056622 hasAuthorship W4387056622A5037098300 @default.
- W4387056622 hasAuthorship W4387056622A5039417073 @default.
- W4387056622 hasAuthorship W4387056622A5046527432 @default.
- W4387056622 hasConcept C110384440 @default.
- W4387056622 hasConcept C115961682 @default.
- W4387056622 hasConcept C137800194 @default.
- W4387056622 hasConcept C153180895 @default.
- W4387056622 hasConcept C154945302 @default.
- W4387056622 hasConcept C2779679103 @default.
- W4387056622 hasConcept C2780056265 @default.
- W4387056622 hasConcept C31972630 @default.
- W4387056622 hasConcept C41008148 @default.
- W4387056622 hasConcept C76155785 @default.
- W4387056622 hasConcept C87133666 @default.
- W4387056622 hasConceptScore W4387056622C110384440 @default.
- W4387056622 hasConceptScore W4387056622C115961682 @default.
- W4387056622 hasConceptScore W4387056622C137800194 @default.
- W4387056622 hasConceptScore W4387056622C153180895 @default.
- W4387056622 hasConceptScore W4387056622C154945302 @default.
- W4387056622 hasConceptScore W4387056622C2779679103 @default.
- W4387056622 hasConceptScore W4387056622C2780056265 @default.
- W4387056622 hasConceptScore W4387056622C31972630 @default.
- W4387056622 hasConceptScore W4387056622C41008148 @default.
- W4387056622 hasConceptScore W4387056622C76155785 @default.
- W4387056622 hasConceptScore W4387056622C87133666 @default.
- W4387056622 hasFunder F4320321001 @default.
- W4387056622 hasLocation W43870566221 @default.
- W4387056622 hasOpenAccess W4387056622 @default.
- W4387056622 hasPrimaryLocation W43870566221 @default.
- W4387056622 hasRelatedWork W1983892167 @default.
- W4387056622 hasRelatedWork W1991429770 @default.
- W4387056622 hasRelatedWork W2281134365 @default.
- W4387056622 hasRelatedWork W2607795551 @default.
- W4387056622 hasRelatedWork W3081760643 @default.
- W4387056622 hasRelatedWork W3155117723 @default.
- W4387056622 hasRelatedWork W3199004353 @default.
- W4387056622 hasRelatedWork W4306309518 @default.
- W4387056622 hasRelatedWork W4385574037 @default.
- W4387056622 hasRelatedWork W4386075645 @default.
- W4387056622 hasVolume "238" @default.
- W4387056622 isParatext "false" @default.
- W4387056622 isRetracted "false" @default.
- W4387056622 workType "article" @default.