FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2888395215> ?p ?o ?g. }

• W2888395215 endingPage "745" @default.
• W2888395215 startingPage "731" @default.
• W2888395215 abstract "Image restoration (IR) problems are very important in many low-level vision tasks. Due to their ill-posed natures, image priors are widely used to regularize the solution spaces. Recently, patch-based non-local self-similarity has shown great potential in IR problems, leading to many effective non-local priors. Their performance largely depends on whether the non-local self-similarity of the underlying image can be fully exploited. However, most of these priors, including non-local regression (NLR), only utilize the center pixel of each patch to model the non-local feature, which is suboptimal. We propose an effective overlap-based non-local regression (ONLR) to fully exploit the non-local similar patches: first, the concept of overlap-based similar pixels group (OSPG) is introduced; second, for each pixel within an OSPG, the non-local weight is obtained via a novel similarity measurement method; third, based on the consistency assumption, the non-local fitting deviations (NLFDs) by using OSPGs are uniformly constrained. Because of the uniform constraints, the restoration may be poor in regions where OSPGs are not reliable. Consequently, a weighting scheme is proposed to measure the OSPG reliability, leading to a novel adjusted non-local regression (ANLR). In addition, the integral image technique (IIT) is adopted to speed up the similar patches search process. To further boost the ANLR, a local directional smoothness (DS) prior is proposed as a good complement of the non-local feature. Finally, a fast split Bregman iteration algorithm is designed to solve the ANLR-DS minimization problem. Extensive experiments on two typical IR problems, that is, image deblurring and super resolution, demonstrate the superiority of the proposed method compared to many state-of-the-art IR methods." @default.
• W2888395215 created "2018-08-31" @default.
• W2888395215 creator A5002282875 @default.
• W2888395215 creator A5028800313 @default.
• W2888395215 creator A5029742741 @default.
• W2888395215 date "2019-03-01" @default.
• W2888395215 modified "2023-10-01" @default.
• W2888395215 title "Adjusted Non-Local Regression and Directional Smoothness for Image Restoration" @default.
• W2888395215 cites W1587448943 @default.
• W2888395215 cites W1885185971 @default.
• W2888395215 cites W1950594372 @default.
• W2888395215 cites W1959857106 @default.
• W2888395215 cites W1978333359 @default.
• W2888395215 cites W1978749115 @default.
• W2888395215 cites W1979331265 @default.
• W2888395215 cites W1992408872 @default.
• W2888395215 cites W1995228944 @default.
• W2888395215 cites W1998419211 @default.
• W2888395215 cites W2002105278 @default.
• W2888395215 cites W2006262236 @default.
• W2888395215 cites W2023926794 @default.
• W2888395215 cites W2045737896 @default.
• W2888395215 cites W2049237558 @default.
• W2888395215 cites W2055784463 @default.
• W2888395215 cites W2060945009 @default.
• W2888395215 cites W2070433376 @default.
• W2888395215 cites W2072238928 @default.
• W2888395215 cites W2077931794 @default.
• W2888395215 cites W2080744942 @default.
• W2888395215 cites W2091494211 @default.
• W2888395215 cites W2097073572 @default.
• W2888395215 cites W2098554565 @default.
• W2888395215 cites W2103559027 @default.
• W2888395215 cites W2113216659 @default.
• W2888395215 cites W2119058682 @default.
• W2888395215 cites W2123613719 @default.
• W2888395215 cites W2132504201 @default.
• W2888395215 cites W2133665775 @default.
• W2888395215 cites W2135089338 @default.
• W2888395215 cites W2137290314 @default.
• W2888395215 cites W2142058898 @default.
• W2888395215 cites W2142224912 @default.
• W2888395215 cites W2150081556 @default.
• W2888395215 cites W2150675091 @default.
• W2888395215 cites W2159080051 @default.
• W2888395215 cites W2164598857 @default.
• W2888395215 cites W2184334976 @default.
• W2888395215 cites W2290736026 @default.
• W2888395215 cites W2324298973 @default.
• W2888395215 cites W2331619054 @default.
• W2888395215 cites W2474073286 @default.
• W2888395215 cites W2484066143 @default.
• W2888395215 cites W2509348655 @default.
• W2888395215 cites W2527019762 @default.
• W2888395215 cites W2594827121 @default.
• W2888395215 cites W2599698286 @default.
• W2888395215 cites W2766739658 @default.
• W2888395215 cites W3104720471 @default.
• W2888395215 cites W4292363360 @default.
• W2888395215 cites W99498721 @default.
• W2888395215 doi "https://doi.org/10.1109/tmm.2018.2866362" @default.
• W2888395215 hasPublicationYear "2019" @default.
• W2888395215 type Work @default.
• W2888395215 sameAs 2888395215 @default.
• W2888395215 citedByCount "28" @default.
• W2888395215 countsByYear W28883952152019 @default.
• W2888395215 countsByYear W28883952152020 @default.
• W2888395215 countsByYear W28883952152021 @default.
• W2888395215 countsByYear W28883952152022 @default.
• W2888395215 countsByYear W28883952152023 @default.
• W2888395215 crossrefType "journal-article" @default.
• W2888395215 hasAuthorship W2888395215A5002282875 @default.
• W2888395215 hasAuthorship W2888395215A5028800313 @default.
• W2888395215 hasAuthorship W2888395215A5029742741 @default.
• W2888395215 hasConcept C102634674 @default.
• W2888395215 hasConcept C103278499 @default.
• W2888395215 hasConcept C105795698 @default.
• W2888395215 hasConcept C106430172 @default.
• W2888395215 hasConcept C107673813 @default.
• W2888395215 hasConcept C11413529 @default.
• W2888395215 hasConcept C115961682 @default.
• W2888395215 hasConcept C120068334 @default.
• W2888395215 hasConcept C126838900 @default.
• W2888395215 hasConcept C134306372 @default.
• W2888395215 hasConcept C138885662 @default.
• W2888395215 hasConcept C141934464 @default.
• W2888395215 hasConcept C153180895 @default.
• W2888395215 hasConcept C154945302 @default.
• W2888395215 hasConcept C160633673 @default.
• W2888395215 hasConcept C177769412 @default.
• W2888395215 hasConcept C183115368 @default.
• W2888395215 hasConcept C2776401178 @default.
• W2888395215 hasConcept C33923547 @default.
• W2888395215 hasConcept C41008148 @default.
• W2888395215 hasConcept C41895202 @default.
• W2888395215 hasConcept C60316415 @default.
• W2888395215 hasConcept C71924100 @default.
• W2888395215 hasConcept C83546350 @default.

• next