Matches in SemOpenAlex for { <https://semopenalex.org/work/W3035355889> ?p ?o ?g. }
Showing items 1 to 95 of
95
with 100 items per page.
- W3035355889 abstract "Non-blind deblurring is an important problem encountered in many image restoration tasks. The focus of non-blind deblurring is on how to suppress noise magnification during deblurring. In practice, it often happens that the noise level of input image is unknown and varies among different images. This paper aims at developing a deep learning framework for deblurring images with unknown noise level. Based on the framework of variational expectation maximization (EM), an iterative noise-blind deblurring scheme is proposed which integrates the estimation of noise level and the quantification of image prior uncertainty. Then, the proposed scheme is unrolled to a neural network (NN) where image prior is modeled by NN with uncertainty quantification. Extensive experiments showed that the proposed method not only outperformed existing noise-blind deblurring methods by a large margin, but also outperformed those state-of-the-art image deblurring methods designed/trained with known noise level." @default.
- W3035355889 created "2020-06-19" @default.
- W3035355889 creator A5030046423 @default.
- W3035355889 creator A5038130835 @default.
- W3035355889 creator A5057717244 @default.
- W3035355889 date "2020-06-01" @default.
- W3035355889 modified "2023-10-01" @default.
- W3035355889 title "Variational-EM-Based Deep Learning for Noise-Blind Image Deblurring" @default.
- W3035355889 cites W1805346680 @default.
- W3035355889 cites W1973567017 @default.
- W3035355889 cites W1978749115 @default.
- W3035355889 cites W2011181254 @default.
- W3035355889 cites W2023005931 @default.
- W3035355889 cites W2025900737 @default.
- W3035355889 cites W2036682493 @default.
- W3035355889 cites W2053968746 @default.
- W3035355889 cites W2110158442 @default.
- W3035355889 cites W2130975789 @default.
- W3035355889 cites W2131686571 @default.
- W3035355889 cites W2171664034 @default.
- W3035355889 cites W2172275395 @default.
- W3035355889 cites W2181619750 @default.
- W3035355889 cites W2421886322 @default.
- W3035355889 cites W2508457857 @default.
- W3035355889 cites W2539781702 @default.
- W3035355889 cites W2552111036 @default.
- W3035355889 cites W2613155248 @default.
- W3035355889 cites W2741183886 @default.
- W3035355889 cites W2776500869 @default.
- W3035355889 cites W2963446712 @default.
- W3035355889 cites W3102025760 @default.
- W3035355889 cites W3123837026 @default.
- W3035355889 cites W4214806317 @default.
- W3035355889 doi "https://doi.org/10.1109/cvpr42600.2020.00368" @default.
- W3035355889 hasPublicationYear "2020" @default.
- W3035355889 type Work @default.
- W3035355889 sameAs 3035355889 @default.
- W3035355889 citedByCount "25" @default.
- W3035355889 countsByYear W30353558892020 @default.
- W3035355889 countsByYear W30353558892021 @default.
- W3035355889 countsByYear W30353558892022 @default.
- W3035355889 countsByYear W30353558892023 @default.
- W3035355889 crossrefType "proceedings-article" @default.
- W3035355889 hasAuthorship W3035355889A5030046423 @default.
- W3035355889 hasAuthorship W3035355889A5038130835 @default.
- W3035355889 hasAuthorship W3035355889A5057717244 @default.
- W3035355889 hasConcept C105795698 @default.
- W3035355889 hasConcept C106430172 @default.
- W3035355889 hasConcept C115961682 @default.
- W3035355889 hasConcept C120665830 @default.
- W3035355889 hasConcept C121332964 @default.
- W3035355889 hasConcept C153180895 @default.
- W3035355889 hasConcept C154945302 @default.
- W3035355889 hasConcept C182081679 @default.
- W3035355889 hasConcept C192209626 @default.
- W3035355889 hasConcept C2777693668 @default.
- W3035355889 hasConcept C31972630 @default.
- W3035355889 hasConcept C33923547 @default.
- W3035355889 hasConcept C41008148 @default.
- W3035355889 hasConcept C49781872 @default.
- W3035355889 hasConcept C9417928 @default.
- W3035355889 hasConcept C99498987 @default.
- W3035355889 hasConceptScore W3035355889C105795698 @default.
- W3035355889 hasConceptScore W3035355889C106430172 @default.
- W3035355889 hasConceptScore W3035355889C115961682 @default.
- W3035355889 hasConceptScore W3035355889C120665830 @default.
- W3035355889 hasConceptScore W3035355889C121332964 @default.
- W3035355889 hasConceptScore W3035355889C153180895 @default.
- W3035355889 hasConceptScore W3035355889C154945302 @default.
- W3035355889 hasConceptScore W3035355889C182081679 @default.
- W3035355889 hasConceptScore W3035355889C192209626 @default.
- W3035355889 hasConceptScore W3035355889C2777693668 @default.
- W3035355889 hasConceptScore W3035355889C31972630 @default.
- W3035355889 hasConceptScore W3035355889C33923547 @default.
- W3035355889 hasConceptScore W3035355889C41008148 @default.
- W3035355889 hasConceptScore W3035355889C49781872 @default.
- W3035355889 hasConceptScore W3035355889C9417928 @default.
- W3035355889 hasConceptScore W3035355889C99498987 @default.
- W3035355889 hasLocation W30353558891 @default.
- W3035355889 hasOpenAccess W3035355889 @default.
- W3035355889 hasPrimaryLocation W30353558891 @default.
- W3035355889 hasRelatedWork W2008178540 @default.
- W3035355889 hasRelatedWork W2013725854 @default.
- W3035355889 hasRelatedWork W2060018053 @default.
- W3035355889 hasRelatedWork W2094238738 @default.
- W3035355889 hasRelatedWork W2354226224 @default.
- W3035355889 hasRelatedWork W2468652750 @default.
- W3035355889 hasRelatedWork W2906703443 @default.
- W3035355889 hasRelatedWork W3194988670 @default.
- W3035355889 hasRelatedWork W4313023825 @default.
- W3035355889 hasRelatedWork W3137059050 @default.
- W3035355889 isParatext "false" @default.
- W3035355889 isRetracted "false" @default.
- W3035355889 magId "3035355889" @default.
- W3035355889 workType "article" @default.