FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3209180049> ?p ?o ?g. }

• W3209180049 endingPage "217" @default.
• W3209180049 startingPage "203" @default.
• W3209180049 abstract "Compressive imaging aims to recover a latent image from under-sampled measurements, suffering from a serious ill-posed inverse problem. Recently, deep neural networks have been applied to this problem with superior results, owing to the learned advanced image priors. These approaches, however, require training separate models for different imaging modalities and sampling ratios, leading to overfitting to specific settings. In this paper, a dynamic proximal unrolling network (dubbed DPUNet) was proposed, which can handle a variety of measurement matrices via one single model without retraining. Specifically, DPUNet can exploit both the embedded observation model via gradient descent and imposed image priors by learned dynamic proximal operators, achieving joint reconstruction. A key component of DPUNet is a dynamic proximal mapping module, whose parameters can be dynamically adjusted at the inference stage and make it adapt to different imaging settings. Moreover, in order to eliminate the image blocking artifacts, an enhanced version DPUNet+ is developed, which integrates a dynamic deblocking module and reconstructs jointly with DPUNet to further improve the performance. Experimental results demonstrate that the proposed method can effectively handle multiple compressive imaging modalities under varying sampling ratios and noise levels via only one trained model, and outperform the state-of-the-art approaches. Our code is available at https://github.com/Yixiao-Yang/DPUNet-PyTorch." @default.
• W3209180049 created "2021-11-08" @default.
• W3209180049 creator A5041130370 @default.
• W3209180049 creator A5067800206 @default.
• W3209180049 creator A5070971509 @default.
• W3209180049 creator A5083586618 @default.
• W3209180049 date "2022-10-01" @default.
• W3209180049 modified "2023-10-18" @default.
• W3209180049 title "Dynamic proximal unrolling network for compressive imaging" @default.
• W3209180049 cites W1901129140 @default.
• W3209180049 cites W1935101545 @default.
• W3209180049 cites W1996726072 @default.
• W3209180049 cites W2011710850 @default.
• W3209180049 cites W2018990310 @default.
• W3209180049 cites W2025976924 @default.
• W3209180049 cites W2029816571 @default.
• W3209180049 cites W2045737896 @default.
• W3209180049 cites W2055191162 @default.
• W3209180049 cites W2070544768 @default.
• W3209180049 cites W2093329260 @default.
• W3209180049 cites W2100556411 @default.
• W3209180049 cites W2100705753 @default.
• W3209180049 cites W2101675075 @default.
• W3209180049 cites W2112050657 @default.
• W3209180049 cites W2122548617 @default.
• W3209180049 cites W2130120519 @default.
• W3209180049 cites W2131752914 @default.
• W3209180049 cites W2141168890 @default.
• W3209180049 cites W2145614561 @default.
• W3209180049 cites W2163973643 @default.
• W3209180049 cites W2168668658 @default.
• W3209180049 cites W2302255633 @default.
• W3209180049 cites W2304034118 @default.
• W3209180049 cites W2500374603 @default.
• W3209180049 cites W2536599074 @default.
• W3209180049 cites W2590877996 @default.
• W3209180049 cites W2619204584 @default.
• W3209180049 cites W2773335402 @default.
• W3209180049 cites W2962696956 @default.
• W3209180049 cites W2963081547 @default.
• W3209180049 cites W2963676935 @default.
• W3209180049 cites W2964082260 @default.
• W3209180049 cites W2964251511 @default.
• W3209180049 cites W3000998666 @default.
• W3209180049 cites W3009991223 @default.
• W3209180049 cites W3048134800 @default.
• W3209180049 cites W3102206315 @default.
• W3209180049 cites W3103875018 @default.
• W3209180049 cites W3115447952 @default.
• W3209180049 cites W3134510327 @default.
• W3209180049 cites W3149183124 @default.
• W3209180049 cites W3189845786 @default.
• W3209180049 cites W4250955649 @default.
• W3209180049 cites W54257720 @default.
• W3209180049 doi "https://doi.org/10.1016/j.neucom.2022.08.034" @default.
• W3209180049 hasPublicationYear "2022" @default.
• W3209180049 type Work @default.
• W3209180049 sameAs 3209180049 @default.
• W3209180049 citedByCount "1" @default.
• W3209180049 countsByYear W32091800492023 @default.
• W3209180049 crossrefType "journal-article" @default.
• W3209180049 hasAuthorship W3209180049A5041130370 @default.
• W3209180049 hasAuthorship W3209180049A5067800206 @default.
• W3209180049 hasAuthorship W3209180049A5070971509 @default.
• W3209180049 hasAuthorship W3209180049A5083586618 @default.
• W3209180049 hasBestOaLocation W32091800492 @default.
• W3209180049 hasConcept C107673813 @default.
• W3209180049 hasConcept C115961682 @default.
• W3209180049 hasConcept C119857082 @default.
• W3209180049 hasConcept C124851039 @default.
• W3209180049 hasConcept C126838900 @default.
• W3209180049 hasConcept C143409427 @default.
• W3209180049 hasConcept C153180895 @default.
• W3209180049 hasConcept C154945302 @default.
• W3209180049 hasConcept C177769412 @default.
• W3209180049 hasConcept C22019652 @default.
• W3209180049 hasConcept C2776145597 @default.
• W3209180049 hasConcept C2776214188 @default.
• W3209180049 hasConcept C41008148 @default.
• W3209180049 hasConcept C41727105 @default.
• W3209180049 hasConcept C50644808 @default.
• W3209180049 hasConcept C71924100 @default.
• W3209180049 hasConcept C99498987 @default.
• W3209180049 hasConceptScore W3209180049C107673813 @default.
• W3209180049 hasConceptScore W3209180049C115961682 @default.
• W3209180049 hasConceptScore W3209180049C119857082 @default.
• W3209180049 hasConceptScore W3209180049C124851039 @default.
• W3209180049 hasConceptScore W3209180049C126838900 @default.
• W3209180049 hasConceptScore W3209180049C143409427 @default.
• W3209180049 hasConceptScore W3209180049C153180895 @default.
• W3209180049 hasConceptScore W3209180049C154945302 @default.
• W3209180049 hasConceptScore W3209180049C177769412 @default.
• W3209180049 hasConceptScore W3209180049C22019652 @default.
• W3209180049 hasConceptScore W3209180049C2776145597 @default.
• W3209180049 hasConceptScore W3209180049C2776214188 @default.
• W3209180049 hasConceptScore W3209180049C41008148 @default.
• W3209180049 hasConceptScore W3209180049C41727105 @default.
• W3209180049 hasConceptScore W3209180049C50644808 @default.

• next