Image Denoising using Attention-Residual Convolutional Neural Networks

Registro completo de metadados
MetadadosDescriçãoIdioma
Autor(es): dc.contributorUniversidade Estadual Paulista (Unesp)-
Autor(es): dc.contributorUniversidade Federal de São Carlos (UFSCar)-
Autor(es): dc.creatorPires, Rafael G. [UNESP]-
Autor(es): dc.creatorSantos, Daniel F. S. [UNESP]-
Autor(es): dc.creatorSantos, Claudio F. G.-
Autor(es): dc.creatorSantana, Marcos C. S. [UNESP]-
Autor(es): dc.creatorPapa, Joao P. [UNESP]-
Autor(es): dc.creatorIEEE-
Data de aceite: dc.date.accessioned2022-02-22T00:59:32Z-
Data de disponibilização: dc.date.available2022-02-22T00:59:32Z-
Data de envio: dc.date.issued2021-06-25-
Data de envio: dc.date.issued2021-06-25-
Data de envio: dc.date.issued2019-12-31-
Fonte completa do material: dc.identifierhttp://dx.doi.org/10.1109/SIBGRAPI51738.2020.00022-
Fonte completa do material: dc.identifierhttp://hdl.handle.net/11449/210333-
Fonte: dc.identifier.urihttp://educapes.capes.gov.br/handle/11449/210333-
Descrição: dc.descriptionDuring the image acquisition process, noise is usually added to the data mainly due to physical limitations of the acquisition sensor, and also regarding imprecisions during the data transmission and manipulation. In that sense, the resultant image needs to be processed to attenuate its noise without losing details. Non-learning-based strategies such as filter-based and noise prior modeling have been adopted to solve the image denoising problem. Nowadays, learning-based denoising techniques showed to be much more effective and flexible approaches, such as Residual Convolutional Neural Networks. Here, we propose a new learning-based non-blind denoising technique named Attention Residual Convolutional Neural Network (ARCNN), and its extension to blind denoising named Flexible Attention Residual Convolutional Neural Network (FARCNN). The proposed methods try to learn the underlying noise expectation using an Attention-Residual mechanism. Experiments on public datasets corrupted by different levels of Gaussian and Poisson noise support the effectiveness of the proposed approaches against some state-of-the-art image denoising methods. ARCNN achieved an overall average PSNR results of around 0.44dB and 0.96dB for Gaussian and Poisson denoising, respectively FARCNN presented very consistent results, even with slightly worsen performance compared to ARCNN.-
Descrição: dc.descriptionConselho Nacional de Desenvolvimento Científico e Tecnológico (CNPq)-
Descrição: dc.descriptionFundação de Amparo à Pesquisa do Estado de São Paulo (FAPESP)-
Descrição: dc.descriptionPetrobras-
Descrição: dc.descriptionNVIDIA-
Descrição: dc.descriptionSao Paulo State Univ, Dept Comp, Bauru, SP, Brazil-
Descrição: dc.descriptionUniv Fed Sao Carlos, Dept Comp, Sao Carlos, SP, Brazil-
Descrição: dc.descriptionSao Paulo State Univ, Dept Comp, Bauru, SP, Brazil-
Descrição: dc.descriptionCNPq: 307066/20177-
Descrição: dc.descriptionCNPq: 427968/2018-6-
Descrição: dc.descriptionFAPESP: 2013/07375-0-
Descrição: dc.descriptionFAPESP: 2014/12236-1-
Descrição: dc.descriptionPetrobras: 2017/00285-6-
Formato: dc.format101-107-
Idioma: dc.languageen-
Publicador: dc.publisherIeee-
Relação: dc.relation2020 33rd Sibgrapi Conference On Graphics, Patterns And Images (sibgrapi 2020)-
???dc.source???: dc.sourceWeb of Science-
Título: dc.titleImage Denoising using Attention-Residual Convolutional Neural Networks-
Aparece nas coleções:Repositório Institucional - Unesp

Não existem arquivos associados a este item.