NoiseNet Signal-Dependent Noise Variance Estimation with Convolutional Neural Network

Abstract : In this paper, the problem of blind estimation of uncorrelated signal-dependent noise parameters in images is formulated as a regression problem with uncertainty. It is shown that this regression task can be effectively solved by a properly trained deep convolution neural network (CNN), called NoiseNet, comprising regressor branch and uncertainty quantifier branch. The former predicts noise standard deviation (STD) for a 32 × 32 pixels image patch, while the latter predicts STD of regressor error. The NoiseNet architecture is proposed and peculiarities of its training are discussed. Signal-dependent noise parameters are estimated by robust iterative processing of many local estimates provided by the NoiseNet. The comparative analysis for real data from NED2012 database is carried out. Its results show that the NoiseNet provides accuracy better than the state-of-the-art existing methods. © 2018, Springer Nature Switzerland AG.
Document type :
Conference papers
Complete list of metadatas

https://hal-univ-rennes1.archives-ouvertes.fr/hal-01904633
Contributor : Laurent Jonchère <>
Submitted on : Thursday, October 25, 2018 - 11:00:59 AM
Last modification on : Friday, August 9, 2019 - 2:26:02 PM

Identifiers

Citation

M. Uss, B. Vozel, V. Lukin, K. Chehdi. NoiseNet Signal-Dependent Noise Variance Estimation with Convolutional Neural Network. 19th International Conference on Advanced Concepts for Intelligent Vision Systems, ACIVS 2018, Sep 2018, Poitiers, France. pp.414-425, ⟨10.1007/978-3-030-01449-0_35⟩. ⟨hal-01904633⟩

Share

Metrics

Record views

71