FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3197788104> ?p ?o ?g. }

• W3197788104 endingPage "116449" @default.
• W3197788104 startingPage "116449" @default.
• W3197788104 abstract "Image restoration is essentially recognized as an ill-posed problem. A promising solution in recent years is incorporating deep network-driven priors into the iterative restoration procedure as constrained conditions. Among them, deep mean-shift prior utilizes the denoising autoencoder to play the role of prior updating. In this study, we present multiple wavelets guided deep mean-shift prior, which integrates the advantages of structural representation in the wavelet transform and learning ability in deep network. Specifically, by re-arranging the multi-view and multi-resolution features generated by multiple wavelet transforms as the input of denoising autoencoder, a more powerful prior information is learned. It benefits from the recurrent structure-preserving and multi-view complementary aggregation properties. We embed the learned prior information into the iterative recovery process and adopt proximal gradient descent to tackle it. Extensive experiments on image deblurring and compressed sensing tasks demonstrated significantly improved performances both visually and quantitatively." @default.
• W3197788104 created "2021-09-13" @default.
• W3197788104 creator A5011540763 @default.
• W3197788104 creator A5038444851 @default.
• W3197788104 creator A5049459284 @default.
• W3197788104 creator A5057647276 @default.
• W3197788104 creator A5063982212 @default.
• W3197788104 creator A5075969066 @default.
• W3197788104 date "2021-11-01" @default.
• W3197788104 modified "2023-10-08" @default.
• W3197788104 title "Multi-wavelet guided deep mean-shift prior for image restoration" @default.
• W3197788104 cites W1964744380 @default.
• W3197788104 cites W1970352604 @default.
• W3197788104 cites W1978749115 @default.
• W3197788104 cites W1992309968 @default.
• W3197788104 cites W1996021349 @default.
• W3197788104 cites W2018990310 @default.
• W3197788104 cites W2019195278 @default.
• W3197788104 cites W2022816471 @default.
• W3197788104 cites W2048695508 @default.
• W3197788104 cites W2054855363 @default.
• W3197788104 cites W2056370875 @default.
• W3197788104 cites W2091540466 @default.
• W3197788104 cites W2093621384 @default.
• W3197788104 cites W2103559027 @default.
• W3197788104 cites W2108207814 @default.
• W3197788104 cites W2110505738 @default.
• W3197788104 cites W2110580418 @default.
• W3197788104 cites W2121058967 @default.
• W3197788104 cites W2130184048 @default.
• W3197788104 cites W2132984323 @default.
• W3197788104 cites W2133665775 @default.
• W3197788104 cites W2159766410 @default.
• W3197788104 cites W2160547390 @default.
• W3197788104 cites W2164566711 @default.
• W3197788104 cites W2165902824 @default.
• W3197788104 cites W2304034118 @default.
• W3197788104 cites W2338117771 @default.
• W3197788104 cites W2364079053 @default.
• W3197788104 cites W2523976623 @default.
• W3197788104 cites W2551161082 @default.
• W3197788104 cites W2604885021 @default.
• W3197788104 cites W2613155248 @default.
• W3197788104 cites W2741137940 @default.
• W3197788104 cites W2741196023 @default.
• W3197788104 cites W2776107444 @default.
• W3197788104 cites W2793829147 @default.
• W3197788104 cites W2895931095 @default.
• W3197788104 cites W2962935835 @default.
• W3197788104 cites W2963494934 @default.
• W3197788104 cites W2963774720 @default.
• W3197788104 cites W2966397867 @default.
• W3197788104 cites W2983469640 @default.
• W3197788104 cites W2991630443 @default.
• W3197788104 cites W3102025760 @default.
• W3197788104 cites W3137074406 @default.
• W3197788104 cites W4247043502 @default.
• W3197788104 doi "https://doi.org/10.1016/j.image.2021.116449" @default.
• W3197788104 hasPublicationYear "2021" @default.
• W3197788104 type Work @default.
• W3197788104 sameAs 3197788104 @default.
• W3197788104 citedByCount "3" @default.
• W3197788104 countsByYear W31977881042022 @default.
• W3197788104 countsByYear W31977881042023 @default.
• W3197788104 crossrefType "journal-article" @default.
• W3197788104 hasAuthorship W3197788104A5011540763 @default.
• W3197788104 hasAuthorship W3197788104A5038444851 @default.
• W3197788104 hasAuthorship W3197788104A5049459284 @default.
• W3197788104 hasAuthorship W3197788104A5057647276 @default.
• W3197788104 hasAuthorship W3197788104A5063982212 @default.
• W3197788104 hasAuthorship W3197788104A5075969066 @default.
• W3197788104 hasConcept C101738243 @default.
• W3197788104 hasConcept C106430172 @default.
• W3197788104 hasConcept C107673813 @default.
• W3197788104 hasConcept C108583219 @default.
• W3197788104 hasConcept C115961682 @default.
• W3197788104 hasConcept C153180895 @default.
• W3197788104 hasConcept C154945302 @default.
• W3197788104 hasConcept C163294075 @default.
• W3197788104 hasConcept C17744445 @default.
• W3197788104 hasConcept C177769412 @default.
• W3197788104 hasConcept C196216189 @default.
• W3197788104 hasConcept C199539241 @default.
• W3197788104 hasConcept C2776359362 @default.
• W3197788104 hasConcept C2777693668 @default.
• W3197788104 hasConcept C31972630 @default.
• W3197788104 hasConcept C41008148 @default.
• W3197788104 hasConcept C47432892 @default.
• W3197788104 hasConcept C9417928 @default.
• W3197788104 hasConcept C94625758 @default.
• W3197788104 hasConceptScore W3197788104C101738243 @default.
• W3197788104 hasConceptScore W3197788104C106430172 @default.
• W3197788104 hasConceptScore W3197788104C107673813 @default.
• W3197788104 hasConceptScore W3197788104C108583219 @default.
• W3197788104 hasConceptScore W3197788104C115961682 @default.
• W3197788104 hasConceptScore W3197788104C153180895 @default.
• W3197788104 hasConceptScore W3197788104C154945302 @default.
• W3197788104 hasConceptScore W3197788104C163294075 @default.

• next