Matches in SemOpenAlex for { <https://semopenalex.org/work/W3197042136> ?p ?o ?g. }
Showing items 1 to 88 of
88
with 100 items per page.
- W3197042136 abstract "This paper proposes a novel Attention-based Multi-Reference Super-resolution network (AMRSR) that, given a low-resolution image, learns to adaptively transfer the most similar texture from multiple reference images to the super-resolution output whilst maintaining spatial coherence. The use of multiple reference images together with attention-based sampling is demonstrated to achieve significantly improved performance over state-of-the-art reference super-resolution approaches on multiple benchmark datasets. Reference super-resolution approaches have recently been proposed to overcome the ill-posed problem of image super-resolution by providing additional information from a high-resolution reference image. Multi-reference super-resolution extends this approach by providing a more diverse pool of image features to overcome the inherent information deficit whilst maintaining memory efficiency. A novel hierarchical attention-based sampling approach is introduced to learn the similarity between low-resolution image features and multiple reference images based on a perceptual loss. Ablation demonstrates the contribution of both multi-reference and hierarchical attention-based sampling to overall performance. Perceptual and quantitative ground-truth evaluation demonstrates significant improvement in performance even when the reference images deviate significantly from the target image. The project website can be found at https://marcopesavento.github.io/AMRSR/" @default.
- W3197042136 created "2021-09-13" @default.
- W3197042136 creator A5068485501 @default.
- W3197042136 creator A5069947751 @default.
- W3197042136 creator A5071852550 @default.
- W3197042136 date "2021-10-01" @default.
- W3197042136 modified "2023-10-17" @default.
- W3197042136 title "Attention-based Multi-Reference Learning for Image Super-Resolution" @default.
- W3197042136 cites W1970260218 @default.
- W3197042136 cites W1975636777 @default.
- W3197042136 cites W1976598894 @default.
- W3197042136 cites W1991867157 @default.
- W3197042136 cites W2020429267 @default.
- W3197042136 cites W2044618760 @default.
- W3197042136 cites W2160014001 @default.
- W3197042136 cites W2194775991 @default.
- W3197042136 cites W2441740088 @default.
- W3197042136 cites W2519207384 @default.
- W3197042136 cites W2741885505 @default.
- W3197042136 cites W2747898905 @default.
- W3197042136 cites W2780544323 @default.
- W3197042136 cites W2799394762 @default.
- W3197042136 cites W2883996939 @default.
- W3197042136 cites W2894343975 @default.
- W3197042136 cites W2919046835 @default.
- W3197042136 cites W2955123570 @default.
- W3197042136 cites W2963372104 @default.
- W3197042136 cites W2963814095 @default.
- W3197042136 cites W2982288888 @default.
- W3197042136 cites W2983339877 @default.
- W3197042136 cites W3014422499 @default.
- W3197042136 cites W3034243376 @default.
- W3197042136 cites W3035022492 @default.
- W3197042136 cites W3035280441 @default.
- W3197042136 cites W3133953507 @default.
- W3197042136 cites W3179253672 @default.
- W3197042136 doi "https://doi.org/10.1109/iccv48922.2021.01443" @default.
- W3197042136 hasPublicationYear "2021" @default.
- W3197042136 type Work @default.
- W3197042136 sameAs 3197042136 @default.
- W3197042136 citedByCount "4" @default.
- W3197042136 countsByYear W31970421362022 @default.
- W3197042136 countsByYear W31970421362023 @default.
- W3197042136 crossrefType "proceedings-article" @default.
- W3197042136 hasAuthorship W3197042136A5068485501 @default.
- W3197042136 hasAuthorship W3197042136A5069947751 @default.
- W3197042136 hasAuthorship W3197042136A5071852550 @default.
- W3197042136 hasBestOaLocation W31970421362 @default.
- W3197042136 hasConcept C106131492 @default.
- W3197042136 hasConcept C115961682 @default.
- W3197042136 hasConcept C13280743 @default.
- W3197042136 hasConcept C140779682 @default.
- W3197042136 hasConcept C153180895 @default.
- W3197042136 hasConcept C154945302 @default.
- W3197042136 hasConcept C185798385 @default.
- W3197042136 hasConcept C205372480 @default.
- W3197042136 hasConcept C205649164 @default.
- W3197042136 hasConcept C31972630 @default.
- W3197042136 hasConcept C41008148 @default.
- W3197042136 hasConceptScore W3197042136C106131492 @default.
- W3197042136 hasConceptScore W3197042136C115961682 @default.
- W3197042136 hasConceptScore W3197042136C13280743 @default.
- W3197042136 hasConceptScore W3197042136C140779682 @default.
- W3197042136 hasConceptScore W3197042136C153180895 @default.
- W3197042136 hasConceptScore W3197042136C154945302 @default.
- W3197042136 hasConceptScore W3197042136C185798385 @default.
- W3197042136 hasConceptScore W3197042136C205372480 @default.
- W3197042136 hasConceptScore W3197042136C205649164 @default.
- W3197042136 hasConceptScore W3197042136C31972630 @default.
- W3197042136 hasConceptScore W3197042136C41008148 @default.
- W3197042136 hasLocation W31970421361 @default.
- W3197042136 hasLocation W31970421362 @default.
- W3197042136 hasOpenAccess W3197042136 @default.
- W3197042136 hasPrimaryLocation W31970421361 @default.
- W3197042136 hasRelatedWork W1485630101 @default.
- W3197042136 hasRelatedWork W1604511055 @default.
- W3197042136 hasRelatedWork W1965875105 @default.
- W3197042136 hasRelatedWork W2026847083 @default.
- W3197042136 hasRelatedWork W2130228941 @default.
- W3197042136 hasRelatedWork W2147047527 @default.
- W3197042136 hasRelatedWork W2161229648 @default.
- W3197042136 hasRelatedWork W2164918837 @default.
- W3197042136 hasRelatedWork W2280716820 @default.
- W3197042136 hasRelatedWork W2993674027 @default.
- W3197042136 isParatext "false" @default.
- W3197042136 isRetracted "false" @default.
- W3197042136 magId "3197042136" @default.
- W3197042136 workType "article" @default.