Matches in SemOpenAlex for { <https://semopenalex.org/work/W4213350433> ?p ?o ?g. }
- W4213350433 abstract "Classic image scaling (e.g. bicubic) can be seen as one convolutional layer and a single upscaling filter. Its implementation is ubiquitous in all display devices and image processing software. In the last decade deep learning systems have been introduced for the task of image super-resolution (SR), using several convolutional layers and numerous filters. These methods have taken over the benchmarks of image quality for upscaling tasks. Would it be possible to replace classic upscalers with deep learning architectures on edge devices such as display panels, tablets, laptop computers, etc.? On one hand, the current trend in Edge–AI chips shows a promising future in this direction, with rapid development of hardware that can run deep–learning tasks efficiently. On the other hand, in image SR only few architectures have pushed the limit to extreme small sizes that can actually run on edge devices at real-time. We explore possible solutions to this problem with the aim to fill the gap between classic upscalers and small deep learning configurations. As a transition from classic to deep–learning upscaling we propose edge–SR (eSR), a set of one–layer architectures that use interpretable mechanisms to upscale images. Certainly, a one–layer architecture cannot reach the quality of deep learning systems. Nevertheless, we find that for high speed requirements, eSR becomes better at trading–off image quality and runtime performance. Filling the gap between classic and deeplearning architectures for image upscaling is critical for massive adoption of this technology. It is equally important to have an interpretable system that can reveal the inner strategies to solve this problem and guide us to future improvements and better understanding of larger networks." @default.
- W4213350433 created "2022-02-24" @default.
- W4213350433 creator A5030144647 @default.
- W4213350433 creator A5048769637 @default.
- W4213350433 creator A5067516422 @default.
- W4213350433 date "2022-01-01" @default.
- W4213350433 modified "2023-10-12" @default.
- W4213350433 title "edge–SR: Super–Resolution For The Masses" @default.
- W4213350433 cites W1930824406 @default.
- W4213350433 cites W1986580369 @default.
- W4213350433 cites W2067042811 @default.
- W4213350433 cites W2068735893 @default.
- W4213350433 cites W2121058967 @default.
- W4213350433 cites W2121927366 @default.
- W4213350433 cites W2140691054 @default.
- W4213350433 cites W2172128189 @default.
- W4213350433 cites W2192954843 @default.
- W4213350433 cites W2194775991 @default.
- W4213350433 cites W2476548250 @default.
- W4213350433 cites W2503339013 @default.
- W4213350433 cites W2741137940 @default.
- W4213350433 cites W2919115771 @default.
- W4213350433 cites W2960833983 @default.
- W4213350433 cites W2963091558 @default.
- W4213350433 cites W2963372104 @default.
- W4213350433 cites W2963446712 @default.
- W4213350433 cites W2964101377 @default.
- W4213350433 cites W2991341034 @default.
- W4213350433 cites W2997139142 @default.
- W4213350433 cites W2999276659 @default.
- W4213350433 cites W3135420168 @default.
- W4213350433 cites W3139549852 @default.
- W4213350433 cites W3143061595 @default.
- W4213350433 cites W3173515979 @default.
- W4213350433 cites W3177328703 @default.
- W4213350433 cites W3207918547 @default.
- W4213350433 doi "https://doi.org/10.1109/wacv51458.2022.00407" @default.
- W4213350433 hasPublicationYear "2022" @default.
- W4213350433 type Work @default.
- W4213350433 citedByCount "5" @default.
- W4213350433 countsByYear W42133504332022 @default.
- W4213350433 countsByYear W42133504332023 @default.
- W4213350433 crossrefType "proceedings-article" @default.
- W4213350433 hasAuthorship W4213350433A5030144647 @default.
- W4213350433 hasAuthorship W4213350433A5048769637 @default.
- W4213350433 hasAuthorship W4213350433A5067516422 @default.
- W4213350433 hasBestOaLocation W42133504332 @default.
- W4213350433 hasConcept C106131492 @default.
- W4213350433 hasConcept C108583219 @default.
- W4213350433 hasConcept C111919701 @default.
- W4213350433 hasConcept C113775141 @default.
- W4213350433 hasConcept C115961682 @default.
- W4213350433 hasConcept C153180895 @default.
- W4213350433 hasConcept C154945302 @default.
- W4213350433 hasConcept C162307627 @default.
- W4213350433 hasConcept C171836373 @default.
- W4213350433 hasConcept C178790620 @default.
- W4213350433 hasConcept C185592680 @default.
- W4213350433 hasConcept C27405340 @default.
- W4213350433 hasConcept C2779227376 @default.
- W4213350433 hasConcept C2780008327 @default.
- W4213350433 hasConcept C31972630 @default.
- W4213350433 hasConcept C41008148 @default.
- W4213350433 hasConcept C49608258 @default.
- W4213350433 hasConcept C81363708 @default.
- W4213350433 hasConcept C9417928 @default.
- W4213350433 hasConceptScore W4213350433C106131492 @default.
- W4213350433 hasConceptScore W4213350433C108583219 @default.
- W4213350433 hasConceptScore W4213350433C111919701 @default.
- W4213350433 hasConceptScore W4213350433C113775141 @default.
- W4213350433 hasConceptScore W4213350433C115961682 @default.
- W4213350433 hasConceptScore W4213350433C153180895 @default.
- W4213350433 hasConceptScore W4213350433C154945302 @default.
- W4213350433 hasConceptScore W4213350433C162307627 @default.
- W4213350433 hasConceptScore W4213350433C171836373 @default.
- W4213350433 hasConceptScore W4213350433C178790620 @default.
- W4213350433 hasConceptScore W4213350433C185592680 @default.
- W4213350433 hasConceptScore W4213350433C27405340 @default.
- W4213350433 hasConceptScore W4213350433C2779227376 @default.
- W4213350433 hasConceptScore W4213350433C2780008327 @default.
- W4213350433 hasConceptScore W4213350433C31972630 @default.
- W4213350433 hasConceptScore W4213350433C41008148 @default.
- W4213350433 hasConceptScore W4213350433C49608258 @default.
- W4213350433 hasConceptScore W4213350433C81363708 @default.
- W4213350433 hasConceptScore W4213350433C9417928 @default.
- W4213350433 hasLocation W42133504331 @default.
- W4213350433 hasLocation W42133504332 @default.
- W4213350433 hasOpenAccess W4213350433 @default.
- W4213350433 hasPrimaryLocation W42133504331 @default.
- W4213350433 hasRelatedWork W2125860982 @default.
- W4213350433 hasRelatedWork W2165172345 @default.
- W4213350433 hasRelatedWork W2350415467 @default.
- W4213350433 hasRelatedWork W2352808182 @default.
- W4213350433 hasRelatedWork W2359696437 @default.
- W4213350433 hasRelatedWork W2361821952 @default.
- W4213350433 hasRelatedWork W2393646612 @default.
- W4213350433 hasRelatedWork W3125054411 @default.
- W4213350433 hasRelatedWork W3159826908 @default.
- W4213350433 hasRelatedWork W980352484 @default.
- W4213350433 isParatext "false" @default.