FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4384564227> ?p ?o ?g. }

• W4384564227 abstract "Ground-based solar image restoration is a computationally expensive procedure that involves nonlinear optimization techniques. The presence of atmospheric turbulence produces perturbations in individual images that make it necessary to apply blind deconvolution techniques. These techniques rely on the observation of many short exposure frames that are used to simultaneously infer the instantaneous state of the atmosphere and the unperturbed object. We have recently explored the use of machine learning to accelerate this process, with promising results. We build upon this previous work to propose several interesting improvements that lead to better models. As well, we propose a new method to accelerate the restoration based on algorithm unrolling. In this method, the image restoration problem is solved with a gradient descent method that is unrolled and accelerated aided by a few small neural networks. The role of the neural networks is to correct the estimation of the solution at each iterative step. The model is trained to perform the optimization in a small fixed number of steps with a curated dataset. Our findings demonstrate that both methods significantly reduce the restoration time compared to the standard optimization procedure. Furthermore, we showcase that these models can be trained in an unsupervised manner using observed images from three different instruments. Remarkably, they also exhibit robust generalization capabilities when applied to new datasets. To foster further research and collaboration, we openly provide the trained models, along with the corresponding training and evaluation code, as well as the training dataset, to the scientific community." @default.
• W4384564227 created "2023-07-18" @default.
• W4384564227 creator A5045963565 @default.
• W4384564227 creator A5053220962 @default.
• W4384564227 creator A5057827143 @default.
• W4384564227 date "2023-07-01" @default.
• W4384564227 modified "2023-09-27" @default.
• W4384564227 title "Accelerating Multiframe Blind Deconvolution via Deep Learning" @default.
• W4384564227 cites W1535651291 @default.
• W4384564227 cites W1980884128 @default.
• W4384564227 cites W1992857901 @default.
• W4384564227 cites W2026214447 @default.
• W4384564227 cites W2027073294 @default.
• W4384564227 cites W2031743920 @default.
• W4384564227 cites W2059157514 @default.
• W4384564227 cites W2072748559 @default.
• W4384564227 cites W2080875179 @default.
• W4384564227 cites W2120185484 @default.
• W4384564227 cites W2146202454 @default.
• W4384564227 cites W2162405008 @default.
• W4384564227 cites W2194775991 @default.
• W4384564227 cites W2576888478 @default.
• W4384564227 cites W2808799744 @default.
• W4384564227 cites W3098645349 @default.
• W4384564227 cites W3103055078 @default.
• W4384564227 cites W3104812948 @default.
• W4384564227 cites W3106518077 @default.
• W4384564227 cites W3119057710 @default.
• W4384564227 cites W3133902371 @default.
• W4384564227 cites W3162265309 @default.
• W4384564227 cites W4319350487 @default.
• W4384564227 doi "https://doi.org/10.1007/s11207-023-02185-8" @default.
• W4384564227 hasPublicationYear "2023" @default.
• W4384564227 type Work @default.
• W4384564227 citedByCount "0" @default.
• W4384564227 crossrefType "journal-article" @default.
• W4384564227 hasAuthorship W4384564227A5045963565 @default.
• W4384564227 hasAuthorship W4384564227A5053220962 @default.
• W4384564227 hasAuthorship W4384564227A5057827143 @default.
• W4384564227 hasBestOaLocation W43845642272 @default.
• W4384564227 hasConcept C106430172 @default.
• W4384564227 hasConcept C111919701 @default.
• W4384564227 hasConcept C11413529 @default.
• W4384564227 hasConcept C115961682 @default.
• W4384564227 hasConcept C119857082 @default.
• W4384564227 hasConcept C134306372 @default.
• W4384564227 hasConcept C153180895 @default.
• W4384564227 hasConcept C153258448 @default.
• W4384564227 hasConcept C154945302 @default.
• W4384564227 hasConcept C174576160 @default.
• W4384564227 hasConcept C177148314 @default.
• W4384564227 hasConcept C177264268 @default.
• W4384564227 hasConcept C199360897 @default.
• W4384564227 hasConcept C2776760102 @default.
• W4384564227 hasConcept C30044814 @default.
• W4384564227 hasConcept C33923547 @default.
• W4384564227 hasConcept C41008148 @default.
• W4384564227 hasConcept C50644808 @default.
• W4384564227 hasConcept C9417928 @default.
• W4384564227 hasConcept C98045186 @default.
• W4384564227 hasConceptScore W4384564227C106430172 @default.
• W4384564227 hasConceptScore W4384564227C111919701 @default.
• W4384564227 hasConceptScore W4384564227C11413529 @default.
• W4384564227 hasConceptScore W4384564227C115961682 @default.
• W4384564227 hasConceptScore W4384564227C119857082 @default.
• W4384564227 hasConceptScore W4384564227C134306372 @default.
• W4384564227 hasConceptScore W4384564227C153180895 @default.
• W4384564227 hasConceptScore W4384564227C153258448 @default.
• W4384564227 hasConceptScore W4384564227C154945302 @default.
• W4384564227 hasConceptScore W4384564227C174576160 @default.
• W4384564227 hasConceptScore W4384564227C177148314 @default.
• W4384564227 hasConceptScore W4384564227C177264268 @default.
• W4384564227 hasConceptScore W4384564227C199360897 @default.
• W4384564227 hasConceptScore W4384564227C2776760102 @default.
• W4384564227 hasConceptScore W4384564227C30044814 @default.
• W4384564227 hasConceptScore W4384564227C33923547 @default.
• W4384564227 hasConceptScore W4384564227C41008148 @default.
• W4384564227 hasConceptScore W4384564227C50644808 @default.
• W4384564227 hasConceptScore W4384564227C9417928 @default.
• W4384564227 hasConceptScore W4384564227C98045186 @default.
• W4384564227 hasFunder F4320315062 @default.
• W4384564227 hasFunder F4320334678 @default.
• W4384564227 hasFunder F4320338337 @default.
• W4384564227 hasIssue "7" @default.
• W4384564227 hasLocation W43845642271 @default.
• W4384564227 hasLocation W43845642272 @default.
• W4384564227 hasOpenAccess W4384564227 @default.
• W4384564227 hasPrimaryLocation W43845642271 @default.
• W4384564227 hasRelatedWork W2012667286 @default.
• W4384564227 hasRelatedWork W2019885600 @default.
• W4384564227 hasRelatedWork W2087099273 @default.
• W4384564227 hasRelatedWork W2136221266 @default.
• W4384564227 hasRelatedWork W2368775331 @default.
• W4384564227 hasRelatedWork W2486108592 @default.
• W4384564227 hasRelatedWork W2626224130 @default.
• W4384564227 hasRelatedWork W2739832043 @default.
• W4384564227 hasRelatedWork W2974904990 @default.
• W4384564227 hasRelatedWork W3137059050 @default.
• W4384564227 hasVolume "298" @default.
• W4384564227 isParatext "false" @default.

• next