Cargando…

Joint Demosaicing and Denoising Based on a Variational Deep Image Prior Neural Network

A joint demosaicing and denoising task refers to the task of simultaneously reconstructing and denoising a color image from a patterned image obtained by a monochrome image sensor with a color filter array. Recently, inspired by the success of deep learning in many image processing tasks, there has...

Descripción completa

Detalles Bibliográficos
Autores principales: Park, Yunjin, Lee, Sukho, Jeong, Byeongseon, Yoon, Jungho
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2020
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7288662/
https://www.ncbi.nlm.nih.gov/pubmed/32456318
http://dx.doi.org/10.3390/s20102970
_version_ 1783545318663520256
author Park, Yunjin
Lee, Sukho
Jeong, Byeongseon
Yoon, Jungho
author_facet Park, Yunjin
Lee, Sukho
Jeong, Byeongseon
Yoon, Jungho
author_sort Park, Yunjin
collection PubMed
description A joint demosaicing and denoising task refers to the task of simultaneously reconstructing and denoising a color image from a patterned image obtained by a monochrome image sensor with a color filter array. Recently, inspired by the success of deep learning in many image processing tasks, there has been research to apply convolutional neural networks (CNNs) to the task of joint demosaicing and denoising. However, such CNNs need many training data to be trained, and work well only for patterned images which have the same amount of noise they have been trained on. In this paper, we propose a variational deep image prior network for joint demosaicing and denoising which can be trained on a single patterned image and works for patterned images with different levels of noise. We also propose a new RGB color filter array (CFA) which works better with the proposed network than the conventional Bayer CFA. Mathematical justifications of why the variational deep image prior network suits the task of joint demosaicing and denoising are also given, and experimental results verify the performance of the proposed method.
format Online
Article
Text
id pubmed-7288662
institution National Center for Biotechnology Information
language English
publishDate 2020
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-72886622020-06-17 Joint Demosaicing and Denoising Based on a Variational Deep Image Prior Neural Network Park, Yunjin Lee, Sukho Jeong, Byeongseon Yoon, Jungho Sensors (Basel) Article A joint demosaicing and denoising task refers to the task of simultaneously reconstructing and denoising a color image from a patterned image obtained by a monochrome image sensor with a color filter array. Recently, inspired by the success of deep learning in many image processing tasks, there has been research to apply convolutional neural networks (CNNs) to the task of joint demosaicing and denoising. However, such CNNs need many training data to be trained, and work well only for patterned images which have the same amount of noise they have been trained on. In this paper, we propose a variational deep image prior network for joint demosaicing and denoising which can be trained on a single patterned image and works for patterned images with different levels of noise. We also propose a new RGB color filter array (CFA) which works better with the proposed network than the conventional Bayer CFA. Mathematical justifications of why the variational deep image prior network suits the task of joint demosaicing and denoising are also given, and experimental results verify the performance of the proposed method. MDPI 2020-05-24 /pmc/articles/PMC7288662/ /pubmed/32456318 http://dx.doi.org/10.3390/s20102970 Text en © 2020 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (http://creativecommons.org/licenses/by/4.0/).
spellingShingle Article
Park, Yunjin
Lee, Sukho
Jeong, Byeongseon
Yoon, Jungho
Joint Demosaicing and Denoising Based on a Variational Deep Image Prior Neural Network
title Joint Demosaicing and Denoising Based on a Variational Deep Image Prior Neural Network
title_full Joint Demosaicing and Denoising Based on a Variational Deep Image Prior Neural Network
title_fullStr Joint Demosaicing and Denoising Based on a Variational Deep Image Prior Neural Network
title_full_unstemmed Joint Demosaicing and Denoising Based on a Variational Deep Image Prior Neural Network
title_short Joint Demosaicing and Denoising Based on a Variational Deep Image Prior Neural Network
title_sort joint demosaicing and denoising based on a variational deep image prior neural network
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7288662/
https://www.ncbi.nlm.nih.gov/pubmed/32456318
http://dx.doi.org/10.3390/s20102970
work_keys_str_mv AT parkyunjin jointdemosaicinganddenoisingbasedonavariationaldeepimagepriorneuralnetwork
AT leesukho jointdemosaicinganddenoisingbasedonavariationaldeepimagepriorneuralnetwork
AT jeongbyeongseon jointdemosaicinganddenoisingbasedonavariationaldeepimagepriorneuralnetwork
AT yoonjungho jointdemosaicinganddenoisingbasedonavariationaldeepimagepriorneuralnetwork