FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2895327470> ?p ?o ?g. }

• W2895327470 endingPage "374" @default.
• W2895327470 startingPage "358" @default.
• W2895327470 abstract "In this paper, we present an end-to-end deblurring network designed specifically for a class of data. Unlike the prior supervised deep-learning works that extensively rely on large sets of paired data, which is highly demanding and challenging to obtain, we propose an unsupervised training scheme with unpaired data to achieve the same. Our model consists of a Generative Adversarial Network (GAN) that learns a strong prior on the clean image domain using adversarial loss and maps the blurred image to its clean equivalent. To improve the stability of GAN and to preserve the image correspondence, we introduce an additional CNN module that reblurs the generated GAN output to match with the blurred input. Along with these two modules, we also make use of the blurred image itself to self-guide the network to constrain the solution space of generated clean images. This self-guidance is achieved by imposing a scale-space gradient error with an additional gradient module. We train our model on different classes and observe that adding the reblur and gradient modules helps in better convergence. Extensive experiments demonstrate that our method performs favorably against the state-of-the-art supervised methods on both synthetic and real-world images even in the absence of any supervision." @default.
• W2895327470 created "2018-10-12" @default.
• W2895327470 creator A5033832521 @default.
• W2895327470 creator A5072108558 @default.
• W2895327470 creator A5074289583 @default.
• W2895327470 date "2018-01-01" @default.
• W2895327470 modified "2023-10-17" @default.
• W2895327470 title "Unsupervised Class-Specific Deblurring" @default.
• W2895327470 cites W1598936309 @default.
• W2895327470 cites W1604428010 @default.
• W2895327470 cites W1834627138 @default.
• W2895327470 cites W1895439721 @default.
• W2895327470 cites W2047123483 @default.
• W2895327470 cites W2114496548 @default.
• W2895327470 cites W2167307343 @default.
• W2895327470 cites W2187997753 @default.
• W2895327470 cites W2204607243 @default.
• W2895327470 cites W2300657047 @default.
• W2895327470 cites W2319561215 @default.
• W2895327470 cites W2331128040 @default.
• W2895327470 cites W233979554 @default.
• W2895327470 cites W2465552163 @default.
• W2895327470 cites W2474628748 @default.
• W2895327470 cites W2475287302 @default.
• W2895327470 cites W2546190447 @default.
• W2895327470 cites W2550673061 @default.
• W2895327470 cites W2560533888 @default.
• W2895327470 cites W2607202125 @default.
• W2895327470 cites W2738579427 @default.
• W2895327470 cites W2740178346 @default.
• W2895327470 cites W2741863916 @default.
• W2895327470 cites W2777194773 @default.
• W2895327470 cites W2780624730 @default.
• W2895327470 cites W2962793481 @default.
• W2895327470 cites W2963073614 @default.
• W2895327470 cites W2963312584 @default.
• W2895327470 cites W2963444790 @default.
• W2895327470 cites W2963470893 @default.
• W2895327470 cites W2963551342 @default.
• W2895327470 cites W2964337079 @default.
• W2895327470 doi "https://doi.org/10.1007/978-3-030-01249-6_22" @default.
• W2895327470 hasPublicationYear "2018" @default.
• W2895327470 type Work @default.
• W2895327470 sameAs 2895327470 @default.
• W2895327470 citedByCount "25" @default.
• W2895327470 countsByYear W28953274702018 @default.
• W2895327470 countsByYear W28953274702019 @default.
• W2895327470 countsByYear W28953274702020 @default.
• W2895327470 countsByYear W28953274702021 @default.
• W2895327470 countsByYear W28953274702022 @default.
• W2895327470 countsByYear W28953274702023 @default.
• W2895327470 crossrefType "book-chapter" @default.
• W2895327470 hasAuthorship W2895327470A5033832521 @default.
• W2895327470 hasAuthorship W2895327470A5072108558 @default.
• W2895327470 hasAuthorship W2895327470A5074289583 @default.
• W2895327470 hasConcept C106430172 @default.
• W2895327470 hasConcept C112972136 @default.
• W2895327470 hasConcept C115961682 @default.
• W2895327470 hasConcept C119857082 @default.
• W2895327470 hasConcept C153180895 @default.
• W2895327470 hasConcept C154945302 @default.
• W2895327470 hasConcept C162324750 @default.
• W2895327470 hasConcept C2777212361 @default.
• W2895327470 hasConcept C2777303404 @default.
• W2895327470 hasConcept C2777693668 @default.
• W2895327470 hasConcept C31972630 @default.
• W2895327470 hasConcept C41008148 @default.
• W2895327470 hasConcept C50522688 @default.
• W2895327470 hasConcept C9417928 @default.
• W2895327470 hasConceptScore W2895327470C106430172 @default.
• W2895327470 hasConceptScore W2895327470C112972136 @default.
• W2895327470 hasConceptScore W2895327470C115961682 @default.
• W2895327470 hasConceptScore W2895327470C119857082 @default.
• W2895327470 hasConceptScore W2895327470C153180895 @default.
• W2895327470 hasConceptScore W2895327470C154945302 @default.
• W2895327470 hasConceptScore W2895327470C162324750 @default.
• W2895327470 hasConceptScore W2895327470C2777212361 @default.
• W2895327470 hasConceptScore W2895327470C2777303404 @default.
• W2895327470 hasConceptScore W2895327470C2777693668 @default.
• W2895327470 hasConceptScore W2895327470C31972630 @default.
• W2895327470 hasConceptScore W2895327470C41008148 @default.
• W2895327470 hasConceptScore W2895327470C50522688 @default.
• W2895327470 hasConceptScore W2895327470C9417928 @default.
• W2895327470 hasLocation W28953274701 @default.
• W2895327470 hasOpenAccess W2895327470 @default.
• W2895327470 hasPrimaryLocation W28953274701 @default.
• W2895327470 hasRelatedWork W2031788393 @default.
• W2895327470 hasRelatedWork W2066613488 @default.
• W2895327470 hasRelatedWork W2182590612 @default.
• W2895327470 hasRelatedWork W2269775642 @default.
• W2895327470 hasRelatedWork W2289746762 @default.
• W2895327470 hasRelatedWork W2315427282 @default.
• W2895327470 hasRelatedWork W3080537281 @default.
• W2895327470 hasRelatedWork W3153582293 @default.
• W2895327470 hasRelatedWork W3207832039 @default.
• W2895327470 hasRelatedWork W791927757 @default.
• W2895327470 isParatext "false" @default.
• W2895327470 isRetracted "false" @default.

• next