FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4313472114> ?p ?o ?g. }

• W4313472114 endingPage "419" @default.
• W4313472114 startingPage "419" @default.
• W4313472114 abstract "To date, the best-performing blind super-resolution (SR) techniques follow one of two paradigms: (A) train standard SR networks on synthetic low-resolution-high-resolution (LR-HR) pairs or (B) predict the degradations of an LR image and then use these to inform a customised SR network. Despite significant progress, subscribers to the former miss out on useful degradation information and followers of the latter rely on weaker SR networks, which are significantly outperformed by the latest architectural advancements. In this work, we present a framework for combining any blind SR prediction mechanism with any deep SR network. We show that a single lightweight metadata insertion block together with a degradation prediction mechanism can allow non-blind SR architectures to rival or outperform state-of-the-art dedicated blind SR networks. We implement various contrastive and iterative degradation prediction schemes and show they are readily compatible with high-performance SR networks such as RCAN and HAN within our framework. Furthermore, we demonstrate our framework's robustness by successfully performing blind SR on images degraded with blurring, noise and compression. This represents the first explicit combined blind prediction and SR of images degraded with such a complex pipeline, acting as a baseline for further advancements." @default.
• W4313472114 created "2023-01-06" @default.
• W4313472114 creator A5007565556 @default.
• W4313472114 creator A5008449368 @default.
• W4313472114 creator A5008794735 @default.
• W4313472114 creator A5024744626 @default.
• W4313472114 creator A5030191054 @default.
• W4313472114 creator A5077265318 @default.
• W4313472114 date "2022-12-30" @default.
• W4313472114 modified "2023-10-05" @default.
• W4313472114 title "The Best of Both Worlds: A Framework for Combining Degradation Prediction with High Performance Super-Resolution Networks" @default.
• W4313472114 cites W1834627138 @default.
• W4313472114 cites W1930824406 @default.
• W4313472114 cites W2110158442 @default.
• W4313472114 cites W2133665775 @default.
• W4313472114 cites W2192954843 @default.
• W4313472114 cites W2194775991 @default.
• W4313472114 cites W2741137940 @default.
• W4313472114 cites W2776107444 @default.
• W4313472114 cites W2792481260 @default.
• W4313472114 cites W2798691622 @default.
• W4313472114 cites W2810821452 @default.
• W4313472114 cites W2891690292 @default.
• W4313472114 cites W2914057590 @default.
• W4313472114 cites W2954930822 @default.
• W4313472114 cites W2962785568 @default.
• W4313472114 cites W2962814024 @default.
• W4313472114 cites W2962903125 @default.
• W4313472114 cites W2963372104 @default.
• W4313472114 cites W2963393566 @default.
• W4313472114 cites W2963470893 @default.
• W4313472114 cites W2963583792 @default.
• W4313472114 cites W2963676087 @default.
• W4313472114 cites W2963704386 @default.
• W4313472114 cites W2964277374 @default.
• W4313472114 cites W2983467712 @default.
• W4313472114 cites W3011456574 @default.
• W4313472114 cites W3013529009 @default.
• W4313472114 cites W3016355810 @default.
• W4313472114 cites W3021946797 @default.
• W4313472114 cites W3034259513 @default.
• W4313472114 cites W3035178397 @default.
• W4313472114 cites W3035524453 @default.
• W4313472114 cites W3039327658 @default.
• W4313472114 cites W3044723170 @default.
• W4313472114 cites W3083728623 @default.
• W4313472114 cites W3138516171 @default.
• W4313472114 cites W3168684807 @default.
• W4313472114 cites W3176334871 @default.
• W4313472114 cites W3180712890 @default.
• W4313472114 cites W3198768110 @default.
• W4313472114 cites W3203631022 @default.
• W4313472114 cites W3204971388 @default.
• W4313472114 cites W3207673409 @default.
• W4313472114 cites W3207918547 @default.
• W4313472114 cites W3209887674 @default.
• W4313472114 cites W4212767839 @default.
• W4313472114 cites W4231059779 @default.
• W4313472114 cites W4233655449 @default.
• W4313472114 cites W4237718774 @default.
• W4313472114 cites W4242919709 @default.
• W4313472114 cites W4280533919 @default.
• W4313472114 cites W4280541456 @default.
• W4313472114 cites W4282937861 @default.
• W4313472114 cites W4283031556 @default.
• W4313472114 cites W4284886326 @default.
• W4313472114 cites W4285159007 @default.
• W4313472114 cites W4287020683 @default.
• W4313472114 cites W4287102299 @default.
• W4313472114 cites W4302604295 @default.
• W4313472114 cites W4312287452 @default.
• W4313472114 cites W4312509301 @default.
• W4313472114 cites W4313161249 @default.
• W4313472114 doi "https://doi.org/10.3390/s23010419" @default.
• W4313472114 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/36617016" @default.
• W4313472114 hasPublicationYear "2022" @default.
• W4313472114 type Work @default.
• W4313472114 citedByCount "0" @default.
• W4313472114 crossrefType "journal-article" @default.
• W4313472114 hasAuthorship W4313472114A5007565556 @default.
• W4313472114 hasAuthorship W4313472114A5008449368 @default.
• W4313472114 hasAuthorship W4313472114A5008794735 @default.
• W4313472114 hasAuthorship W4313472114A5024744626 @default.
• W4313472114 hasAuthorship W4313472114A5030191054 @default.
• W4313472114 hasAuthorship W4313472114A5077265318 @default.
• W4313472114 hasBestOaLocation W43134721141 @default.
• W4313472114 hasConcept C104317684 @default.
• W4313472114 hasConcept C111919701 @default.
• W4313472114 hasConcept C124101348 @default.
• W4313472114 hasConcept C154945302 @default.
• W4313472114 hasConcept C185592680 @default.
• W4313472114 hasConcept C199360897 @default.
• W4313472114 hasConcept C2779679103 @default.
• W4313472114 hasConcept C41008148 @default.
• W4313472114 hasConcept C43521106 @default.
• W4313472114 hasConcept C55493867 @default.
• W4313472114 hasConcept C63479239 @default.
• W4313472114 hasConcept C76155785 @default.

• next