@InProceedings{PiresSanSanSanPap:2020:ImDeUs,
author = "Pires, Rafael Gon{\c{c}}alves and Santos, Daniel Felipe Silva and
Santana, Marcos Cleison Silva and Santos, Claudio Filipe
Gon{\c{c}}alves dos and Papa, Jo{\~a}o Paulo",
affiliation = "{S{\~a}o Paulo State University (UNESP)} and {S{\~a}o Paulo
State University (UNESP)} and {S{\~a}o Paulo State University
(UNESP)} and {Federal University of S{\~a}o Carlos (UFSCAR)} and
{S{\~a}o Paulo State University (UNESP)}",
title = "Image Denoising using Attention-Residual Convolutional Neural
Networks",
booktitle = "Proceedings...",
year = "2020",
editor = "Musse, Soraia Raupp and Cesar Junior, Roberto Marcondes and
Pelechano, Nuria and Wang, Zhangyang (Atlas)",
organization = "Conference on Graphics, Patterns and Images, 33. (SIBGRAPI)",
publisher = "IEEE Computer Society",
address = "Los Alamitos",
keywords = "image restoration, deep learning.",
abstract = "During 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, suchas
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.",
conference-location = "Porto de Galinhas (virtual)",
conference-year = "7-10 Nov. 2020",
doi = "10.1109/SIBGRAPI51738.2020.00022",
url = "http://dx.doi.org/10.1109/SIBGRAPI51738.2020.00022",
language = "en",
ibi = "8JMKD3MGPEW34M/438DG7H",
url = "http://urlib.net/ibi/8JMKD3MGPEW34M/438DG7H",
targetfile = "PID6634881.pdf",
urlaccessdate = "2025, Feb. 16"
}