Matches in SemOpenAlex for { <https://semopenalex.org/work/W3200282037> ?p ?o ?g. }
Showing items 1 to 97 of
97
with 100 items per page.
- W3200282037 endingPage "79" @default.
- W3200282037 startingPage "69" @default.
- W3200282037 abstract "Current deep deblurring methods pay main attention to learning a transferring network to transfer synthetic blurred images to clean ones. Though achieving significant performance on the training datasets, they still suffer from a weaker generalization capability from training datasets to others with different synthetic blurs, thus resulting in significantly inferior performance on testing datasets. In order to alleviate this problem, we propose a latent contrastive model, Blur Distilling and Information Reconstruction Networks (BDIRNet), to learn image prior and improve the robustness of deep deblurring. The proposed BDIRNet consists of a blur removing network (DistillNet) and a reconstruction network (RecNet). Two kinds of images with almost the same information but different qualities are input into DistillNet to extract identical structure information via contrast latent information and purify the perturbations from other unimportant information like blur. While the RecNet is utilized to reconstruct sharp images based on the extracted information. In addition, inside the DistillNet and RecNet, a statistical anti-interference distilling (SAID) and anti-interference reconstruction (SAIR) modules are proposed to further enhance the robustness of our methods, respectively. Extensive experiments on different datasets show that the proposed methods achieve improved and robust results compared to recent state-of-the-art methods." @default.
- W3200282037 created "2021-09-27" @default.
- W3200282037 creator A5004450394 @default.
- W3200282037 creator A5037200751 @default.
- W3200282037 creator A5061507436 @default.
- W3200282037 creator A5066621365 @default.
- W3200282037 creator A5069604707 @default.
- W3200282037 date "2021-11-01" @default.
- W3200282037 modified "2023-09-24" @default.
- W3200282037 title "Deep robust image deblurring via blur distilling and information comparison in latent space" @default.
- W3200282037 cites W2043529138 @default.
- W3200282037 cites W2103913786 @default.
- W3200282037 cites W2121689659 @default.
- W3200282037 cites W2141115311 @default.
- W3200282037 cites W2300657047 @default.
- W3200282037 cites W2777194773 @default.
- W3200282037 cites W2893595367 @default.
- W3200282037 cites W2895327470 @default.
- W3200282037 cites W2895477542 @default.
- W3200282037 cites W2955192444 @default.
- W3200282037 cites W2963667985 @default.
- W3200282037 cites W2964178216 @default.
- W3200282037 cites W2965669158 @default.
- W3200282037 cites W2982795046 @default.
- W3200282037 cites W2987477823 @default.
- W3200282037 cites W3034724715 @default.
- W3200282037 cites W3034770329 @default.
- W3200282037 cites W3034789174 @default.
- W3200282037 cites W3035086889 @default.
- W3200282037 cites W3035212231 @default.
- W3200282037 cites W3101787898 @default.
- W3200282037 doi "https://doi.org/10.1016/j.neucom.2021.09.019" @default.
- W3200282037 hasPublicationYear "2021" @default.
- W3200282037 type Work @default.
- W3200282037 sameAs 3200282037 @default.
- W3200282037 citedByCount "6" @default.
- W3200282037 countsByYear W32002820372022 @default.
- W3200282037 countsByYear W32002820372023 @default.
- W3200282037 crossrefType "journal-article" @default.
- W3200282037 hasAuthorship W3200282037A5004450394 @default.
- W3200282037 hasAuthorship W3200282037A5037200751 @default.
- W3200282037 hasAuthorship W3200282037A5061507436 @default.
- W3200282037 hasAuthorship W3200282037A5066621365 @default.
- W3200282037 hasAuthorship W3200282037A5069604707 @default.
- W3200282037 hasConcept C104317684 @default.
- W3200282037 hasConcept C106430172 @default.
- W3200282037 hasConcept C108583219 @default.
- W3200282037 hasConcept C115961682 @default.
- W3200282037 hasConcept C134306372 @default.
- W3200282037 hasConcept C153180895 @default.
- W3200282037 hasConcept C154945302 @default.
- W3200282037 hasConcept C177148314 @default.
- W3200282037 hasConcept C185592680 @default.
- W3200282037 hasConcept C2777693668 @default.
- W3200282037 hasConcept C31972630 @default.
- W3200282037 hasConcept C33923547 @default.
- W3200282037 hasConcept C41008148 @default.
- W3200282037 hasConcept C55493867 @default.
- W3200282037 hasConcept C63479239 @default.
- W3200282037 hasConcept C9417928 @default.
- W3200282037 hasConceptScore W3200282037C104317684 @default.
- W3200282037 hasConceptScore W3200282037C106430172 @default.
- W3200282037 hasConceptScore W3200282037C108583219 @default.
- W3200282037 hasConceptScore W3200282037C115961682 @default.
- W3200282037 hasConceptScore W3200282037C134306372 @default.
- W3200282037 hasConceptScore W3200282037C153180895 @default.
- W3200282037 hasConceptScore W3200282037C154945302 @default.
- W3200282037 hasConceptScore W3200282037C177148314 @default.
- W3200282037 hasConceptScore W3200282037C185592680 @default.
- W3200282037 hasConceptScore W3200282037C2777693668 @default.
- W3200282037 hasConceptScore W3200282037C31972630 @default.
- W3200282037 hasConceptScore W3200282037C33923547 @default.
- W3200282037 hasConceptScore W3200282037C41008148 @default.
- W3200282037 hasConceptScore W3200282037C55493867 @default.
- W3200282037 hasConceptScore W3200282037C63479239 @default.
- W3200282037 hasConceptScore W3200282037C9417928 @default.
- W3200282037 hasFunder F4320320431 @default.
- W3200282037 hasLocation W32002820371 @default.
- W3200282037 hasOpenAccess W3200282037 @default.
- W3200282037 hasPrimaryLocation W32002820371 @default.
- W3200282037 hasRelatedWork W2008178540 @default.
- W3200282037 hasRelatedWork W2013725854 @default.
- W3200282037 hasRelatedWork W2060018053 @default.
- W3200282037 hasRelatedWork W2094238738 @default.
- W3200282037 hasRelatedWork W2354226224 @default.
- W3200282037 hasRelatedWork W2468652750 @default.
- W3200282037 hasRelatedWork W2906703443 @default.
- W3200282037 hasRelatedWork W3194988670 @default.
- W3200282037 hasRelatedWork W4313023825 @default.
- W3200282037 hasRelatedWork W3137059050 @default.
- W3200282037 hasVolume "466" @default.
- W3200282037 isParatext "false" @default.
- W3200282037 isRetracted "false" @default.
- W3200282037 magId "3200282037" @default.
- W3200282037 workType "article" @default.