Pixelwise Estimation of Signal-Dependent Image Noise Using Deep Residual Learning
In traditional image denoising, noise level is an important scalar parameter which decides how much the input noisy image should be smoothed. Existing noise estimation methods often assume that the noise level is constant at every pixel. However, real-world noise is signal dependent, or the noise le...
Main Authors: | , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Hindawi Limited
2019-01-01
|
Series: | Computational Intelligence and Neuroscience |
Online Access: | http://dx.doi.org/10.1155/2019/4970508 |
id |
doaj-2591ff73712946a584e7d5d4d1512949 |
---|---|
record_format |
Article |
spelling |
doaj-2591ff73712946a584e7d5d4d15129492020-11-25T02:39:51ZengHindawi LimitedComputational Intelligence and Neuroscience1687-52651687-52732019-01-01201910.1155/2019/49705084970508Pixelwise Estimation of Signal-Dependent Image Noise Using Deep Residual LearningHanlin Tan0Huaxin Xiao1Shiming Lai2Yu Liu3Maojun Zhang4College of System Engineering, National University of Defense Technology, Changsha 410073, ChinaCollege of System Engineering, National University of Defense Technology, Changsha 410073, ChinaCollege of System Engineering, National University of Defense Technology, Changsha 410073, ChinaCollege of System Engineering, National University of Defense Technology, Changsha 410073, ChinaCollege of System Engineering, National University of Defense Technology, Changsha 410073, ChinaIn traditional image denoising, noise level is an important scalar parameter which decides how much the input noisy image should be smoothed. Existing noise estimation methods often assume that the noise level is constant at every pixel. However, real-world noise is signal dependent, or the noise level is not constant over the whole image. In this paper, we attempt to estimate the precise and pixelwise noise level instead of a simple global scalar. To the best of our knowledge, this is the first work on the problem. Particularly, we propose a deep convolutional neural network named “deep residual noise estimator” (DRNE) for pixelwise noise-level estimation. We carefully design the architecture of the DRNE, which consists of a stack of customized residual blocks without any pooling or interpolation operation. The proposed DRNE formulates the process of noise estimation as pixel-to-pixel prediction. The experimental results show that the DRNE can achieve better performance on nonhomogeneous noise estimation than state-of-the-art methods. In addition, the DRNE can bring denoising performance gains in removing signal-dependent Gaussian noise when working with recent deep learning denoising methods.http://dx.doi.org/10.1155/2019/4970508 |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Hanlin Tan Huaxin Xiao Shiming Lai Yu Liu Maojun Zhang |
spellingShingle |
Hanlin Tan Huaxin Xiao Shiming Lai Yu Liu Maojun Zhang Pixelwise Estimation of Signal-Dependent Image Noise Using Deep Residual Learning Computational Intelligence and Neuroscience |
author_facet |
Hanlin Tan Huaxin Xiao Shiming Lai Yu Liu Maojun Zhang |
author_sort |
Hanlin Tan |
title |
Pixelwise Estimation of Signal-Dependent Image Noise Using Deep Residual Learning |
title_short |
Pixelwise Estimation of Signal-Dependent Image Noise Using Deep Residual Learning |
title_full |
Pixelwise Estimation of Signal-Dependent Image Noise Using Deep Residual Learning |
title_fullStr |
Pixelwise Estimation of Signal-Dependent Image Noise Using Deep Residual Learning |
title_full_unstemmed |
Pixelwise Estimation of Signal-Dependent Image Noise Using Deep Residual Learning |
title_sort |
pixelwise estimation of signal-dependent image noise using deep residual learning |
publisher |
Hindawi Limited |
series |
Computational Intelligence and Neuroscience |
issn |
1687-5265 1687-5273 |
publishDate |
2019-01-01 |
description |
In traditional image denoising, noise level is an important scalar parameter which decides how much the input noisy image should be smoothed. Existing noise estimation methods often assume that the noise level is constant at every pixel. However, real-world noise is signal dependent, or the noise level is not constant over the whole image. In this paper, we attempt to estimate the precise and pixelwise noise level instead of a simple global scalar. To the best of our knowledge, this is the first work on the problem. Particularly, we propose a deep convolutional neural network named “deep residual noise estimator” (DRNE) for pixelwise noise-level estimation. We carefully design the architecture of the DRNE, which consists of a stack of customized residual blocks without any pooling or interpolation operation. The proposed DRNE formulates the process of noise estimation as pixel-to-pixel prediction. The experimental results show that the DRNE can achieve better performance on nonhomogeneous noise estimation than state-of-the-art methods. In addition, the DRNE can bring denoising performance gains in removing signal-dependent Gaussian noise when working with recent deep learning denoising methods. |
url |
http://dx.doi.org/10.1155/2019/4970508 |
work_keys_str_mv |
AT hanlintan pixelwiseestimationofsignaldependentimagenoiseusingdeepresiduallearning AT huaxinxiao pixelwiseestimationofsignaldependentimagenoiseusingdeepresiduallearning AT shiminglai pixelwiseestimationofsignaldependentimagenoiseusingdeepresiduallearning AT yuliu pixelwiseestimationofsignaldependentimagenoiseusingdeepresiduallearning AT maojunzhang pixelwiseestimationofsignaldependentimagenoiseusingdeepresiduallearning |
_version_ |
1724784464597352448 |