FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4379928090> ?p ?o ?g. }

• W4379928090 endingPage "12" @default.
• W4379928090 startingPage "1" @default.
• W4379928090 abstract "Conventional deconvolution methods utilize hand-crafted image priors to constrain the optimization. While deep-learning-based methods have simplified the optimization by end-to-end training, they fail to generalize well to blurs unseen in the training dataset. Thus, training image-specific models is important for higher generalization. Deep image prior (DIP) provides an approach to optimize the weights of a randomly initialized network with a single degraded image by maximum a posteriori (MAP), which shows that the architecture of a network can serve as the hand-crafted image prior. Unlike conventional hand-crafted image priors, which are obtained through statistical methods, finding a suitable network architecture is challenging due to the unclear relationship between images and their corresponding architectures. As a result, the network architecture cannot provide enough constraint for the latent sharp image. This paper proposes a new variational deep image prior (VDIP) for blind image deconvolution, which exploits additive hand-crafted image priors on latent sharp images and approximates a distribution for each pixel to avoid suboptimal solutions. Our mathematical analysis shows that the proposed method can better constrain the optimization. The experimental results further demonstrate that the generated images have better quality than that of the original DIP on benchmark datasets." @default.
• W4379928090 created "2023-06-09" @default.
• W4379928090 creator A5010575087 @default.
• W4379928090 creator A5026522091 @default.
• W4379928090 creator A5059534928 @default.
• W4379928090 creator A5081300658 @default.
• W4379928090 date "2023-01-01" @default.
• W4379928090 modified "2023-09-27" @default.
• W4379928090 title "Blind Image Deconvolution Using Variational Deep Image Prior" @default.
• W4379928090 cites W1497088612 @default.
• W4379928090 cites W1598281290 @default.
• W4379928090 cites W1795014501 @default.
• W4379928090 cites W1987075379 @default.
• W4379928090 cites W1992309968 @default.
• W4379928090 cites W2036682493 @default.
• W4379928090 cites W2083610878 @default.
• W4379928090 cites W2092264651 @default.
• W4379928090 cites W2102166818 @default.
• W4379928090 cites W2103913786 @default.
• W4379928090 cites W2135238609 @default.
• W4379928090 cites W2138204001 @default.
• W4379928090 cites W2141115311 @default.
• W4379928090 cites W2167053624 @default.
• W4379928090 cites W2167307343 @default.
• W4379928090 cites W2300657047 @default.
• W4379928090 cites W233979554 @default.
• W4379928090 cites W2346276594 @default.
• W4379928090 cites W2396267364 @default.
• W4379928090 cites W2465552163 @default.
• W4379928090 cites W2474628748 @default.
• W4379928090 cites W2519373937 @default.
• W4379928090 cites W2560533888 @default.
• W4379928090 cites W2564023417 @default.
• W4379928090 cites W2740543610 @default.
• W4379928090 cites W2745949522 @default.
• W4379928090 cites W2756389006 @default.
• W4379928090 cites W2777194773 @default.
• W4379928090 cites W2777685367 @default.
• W4379928090 cites W2798735168 @default.
• W4379928090 cites W2905658590 @default.
• W4379928090 cites W2955179830 @default.
• W4379928090 cites W2963130865 @default.
• W4379928090 cites W2963312584 @default.
• W4379928090 cites W2963383962 @default.
• W4379928090 cites W2963667985 @default.
• W4379928090 cites W2963704386 @default.
• W4379928090 cites W2964030969 @default.
• W4379928090 cites W2965217508 @default.
• W4379928090 cites W2965300963 @default.
• W4379928090 cites W2967273822 @default.
• W4379928090 cites W2982374186 @default.
• W4379928090 cites W2982795046 @default.
• W4379928090 cites W2997058852 @default.
• W4379928090 cites W3003954661 @default.
• W4379928090 cites W3013170474 @default.
• W4379928090 cites W3034724715 @default.
• W4379928090 cites W3034789174 @default.
• W4379928090 cites W3035304632 @default.
• W4379928090 cites W3096647320 @default.
• W4379928090 cites W3107405705 @default.
• W4379928090 cites W3109746756 @default.
• W4379928090 cites W3157807191 @default.
• W4379928090 cites W3165930601 @default.
• W4379928090 cites W3167568784 @default.
• W4379928090 cites W3170697543 @default.
• W4379928090 cites W3174154150 @default.
• W4379928090 cites W3175634226 @default.
• W4379928090 cites W3182557492 @default.
• W4379928090 cites W4214815024 @default.
• W4379928090 cites W4225672218 @default.
• W4379928090 cites W4236387761 @default.
• W4379928090 cites W4311415873 @default.
• W4379928090 doi "https://doi.org/10.1109/tpami.2023.3283979" @default.
• W4379928090 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/37289601" @default.
• W4379928090 hasPublicationYear "2023" @default.
• W4379928090 type Work @default.
• W4379928090 citedByCount "0" @default.
• W4379928090 crossrefType "journal-article" @default.
• W4379928090 hasAuthorship W4379928090A5010575087 @default.
• W4379928090 hasAuthorship W4379928090A5026522091 @default.
• W4379928090 hasAuthorship W4379928090A5059534928 @default.
• W4379928090 hasAuthorship W4379928090A5081300658 @default.
• W4379928090 hasConcept C105795698 @default.
• W4379928090 hasConcept C106430172 @default.
• W4379928090 hasConcept C107673813 @default.
• W4379928090 hasConcept C108583219 @default.
• W4379928090 hasConcept C11413529 @default.
• W4379928090 hasConcept C115961682 @default.
• W4379928090 hasConcept C13280743 @default.
• W4379928090 hasConcept C134306372 @default.
• W4379928090 hasConcept C153180895 @default.
• W4379928090 hasConcept C154945302 @default.
• W4379928090 hasConcept C174576160 @default.
• W4379928090 hasConcept C177148314 @default.
• W4379928090 hasConcept C177769412 @default.
• W4379928090 hasConcept C185798385 @default.
• W4379928090 hasConcept C205649164 @default.
• W4379928090 hasConcept C30044814 @default.

• next