Can a Single Image Denoising Neural Network Handle All Levels of Gaussian Noise?

A recently introduced set of deep neural networks designed for the image denoising task achieves state-of-the-art performance. However, they are specialized networks in that each of them can handle just one noise level fixed in their respective training process. In this letter, by investigating the...

Full description

Saved in:
Bibliographic Details
Published in:IEEE signal processing letters 2014-09, Vol.21 (9), p.1150-1153
Main Authors: Yi-Qing Wang, Morel, Jean-Michel
Format: Article
Language:English
Subjects:
Deep neural network
distribution invariance
Gaussian
Gaussian noise
Handles
image denoising
natural patch space
Neural networks
Noise
Noise level
Noise levels
Noise measurement
Noise reduction
Training
Transforms
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:A recently introduced set of deep neural networks designed for the image denoising task achieves state-of-the-art performance. However, they are specialized networks in that each of them can handle just one noise level fixed in their respective training process. In this letter, by investigating the distribution invariance of the natural image patches with respect to linear transforms, we show how to make a single existing deep neural network work well across all levels of Gaussian noise, thereby allowing to significantly reduce the training time for a general-purpose neural network powered denoising algorithm.
ISSN:1070-9908
1558-2361
DOI:10.1109/LSP.2014.2314613