FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2998785217> ?p ?o ?g. }

• W2998785217 endingPage "681" @default.
• W2998785217 startingPage "666" @default.
• W2998785217 abstract "Blind image deblurring remains a topic of enduring interest. Learning based approaches, especially those that employ neural networks have emerged to complement traditional model based methods and in many cases achieve vastly enhanced performance. That said, neural network approaches are generally empirically designed and the underlying structures are difficult to interpret. In recent years, a promising technique called algorithm unrolling has been developed that has helped connect iterative algorithms such as those for sparse coding to neural network architectures. In this article, we propose a neural network architecture based on this idea. We first present an iterative algorithm that may be considered as a generalization of the traditional total-variation regularization method in the gradient domain. We then unroll the algorithm to construct a neural network for image deblurring which we refer to as Deep Unrolling for Blind Deblurring (DUBLID). Key algorithm parameters are learned with the help of training images. Our proposed deep network DUBLID achieves significant practical performance gains while enjoying interpretability and efficiency at the same time. Extensive experimental results show that DUBLID outperforms many state-of-the-art methods and in addition is computationally faster." @default.
• W2998785217 created "2020-01-23" @default.
• W2998785217 creator A5005913897 @default.
• W2998785217 creator A5014013504 @default.
• W2998785217 creator A5014226370 @default.
• W2998785217 creator A5015969128 @default.
• W2998785217 creator A5026535457 @default.
• W2998785217 date "2020-01-01" @default.
• W2998785217 modified "2023-10-16" @default.
• W2998785217 title "Efficient and Interpretable Deep Blind Image Deblurring Via Algorithm Unrolling" @default.
• W2998785217 cites W1457323852 @default.
• W2998785217 cites W1598281290 @default.
• W2998785217 cites W1604428010 @default.
• W2998785217 cites W1795014501 @default.
• W2998785217 cites W1906770428 @default.
• W2998785217 cites W1916935112 @default.
• W2998785217 cites W1919542679 @default.
• W2998785217 cites W1978333359 @default.
• W2998785217 cites W1984859941 @default.
• W2998785217 cites W1987075379 @default.
• W2998785217 cites W1991605728 @default.
• W2998785217 cites W1995551361 @default.
• W2998785217 cites W2027231794 @default.
• W2998785217 cites W2034972122 @default.
• W2998785217 cites W2036682493 @default.
• W2998785217 cites W2043529138 @default.
• W2998785217 cites W2045849979 @default.
• W2998785217 cites W2057477395 @default.
• W2998785217 cites W2069629287 @default.
• W2998785217 cites W2092051980 @default.
• W2998785217 cites W2099628070 @default.
• W2998785217 cites W2103913786 @default.
• W2998785217 cites W2106923440 @default.
• W2998785217 cites W2110158442 @default.
• W2998785217 cites W2112796928 @default.
• W2998785217 cites W2121927366 @default.
• W2998785217 cites W2126097106 @default.
• W2998785217 cites W2132680427 @default.
• W2998785217 cites W2133665775 @default.
• W2998785217 cites W2135238609 @default.
• W2998785217 cites W2161804069 @default.
• W2998785217 cites W2167307343 @default.
• W2998785217 cites W2167767461 @default.
• W2998785217 cites W2170608748 @default.
• W2998785217 cites W2171500271 @default.
• W2998785217 cites W2194775991 @default.
• W2998785217 cites W2242218935 @default.
• W2998785217 cites W2294215176 @default.
• W2998785217 cites W2300657047 @default.
• W2998785217 cites W2331376995 @default.
• W2998785217 cites W2346276594 @default.
• W2998785217 cites W2465552163 @default.
• W2998785217 cites W2560533888 @default.
• W2998785217 cites W2574952845 @default.
• W2998785217 cites W2708797285 @default.
• W2998785217 cites W2737660901 @default.
• W2998785217 cites W2738579427 @default.
• W2998785217 cites W2740543610 @default.
• W2998785217 cites W2756389006 @default.
• W2998785217 cites W2759428153 @default.
• W2998785217 cites W2777194773 @default.
• W2998785217 cites W2780534972 @default.
• W2998785217 cites W2782977076 @default.
• W2998785217 cites W2798735168 @default.
• W2998785217 cites W2798840374 @default.
• W2998785217 cites W2909370557 @default.
• W2998785217 cites W2962708058 @default.
• W2998785217 cites W2962785568 @default.
• W2998785217 cites W2963130865 @default.
• W2998785217 cites W2963312584 @default.
• W2998785217 cites W2964030969 @default.
• W2998785217 cites W2972675027 @default.
• W2998785217 cites W4214815024 @default.
• W2998785217 cites W4232301379 @default.
• W2998785217 cites W4236387761 @default.
• W2998785217 cites W4244769743 @default.
• W2998785217 cites W4251178070 @default.
• W2998785217 cites W4254979477 @default.
• W2998785217 cites W4300263211 @default.
• W2998785217 doi "https://doi.org/10.1109/tci.2020.2964202" @default.
• W2998785217 hasPublicationYear "2020" @default.
• W2998785217 type Work @default.
• W2998785217 sameAs 2998785217 @default.
• W2998785217 citedByCount "101" @default.
• W2998785217 countsByYear W29987852172019 @default.
• W2998785217 countsByYear W29987852172020 @default.
• W2998785217 countsByYear W29987852172021 @default.
• W2998785217 countsByYear W29987852172022 @default.
• W2998785217 countsByYear W29987852172023 @default.
• W2998785217 crossrefType "journal-article" @default.
• W2998785217 hasAuthorship W2998785217A5005913897 @default.
• W2998785217 hasAuthorship W2998785217A5014013504 @default.
• W2998785217 hasAuthorship W2998785217A5014226370 @default.
• W2998785217 hasAuthorship W2998785217A5015969128 @default.
• W2998785217 hasAuthorship W2998785217A5026535457 @default.
• W2998785217 hasBestOaLocation W29987852171 @default.
• W2998785217 hasConcept C106430172 @default.
• W2998785217 hasConcept C108583219 @default.

• next