Blind image denoising via dynamic dual learning

Publication Type

Journal Article

Publication Date

1-2021

Abstract

Existing discriminative learning methods for image denoising use either a single residual learning or a nonresidual learning design. However, we observe that these two schemes perform differently with the same noise level, and yet, there have been no explorations regarding whether residual or nonresidual designs are better suited for denoising. Additionally, many discriminative denoisers are designed to learn a model that corresponds to a fixed noise level, which means that multiple models are required to recover corrupted images with noise at different levels. In this paper, we propose a dynamic dual learning network for blind image denoising, namely, DualBDNet. Instead of modeling a sole task prediction network, the proposed DualBDNet investigates the inherent relations between the residual estimation and the nonresidual estimation. In particular, DualBDNet produces task-dependent feature maps, and each part of the features is devoted to one specific task (residual/nonresidual mapping). To address different noise levels with a single network or even cases where the statistics of noise are unknown, we further introduce an embedded subnetwork into DualBDNet. One output of the subnetwork is the learning of a dynamic compositional attention to highlight the more significant task-dependent feature maps, adaptively coinciding with the extent of corruption. The other output is the learning of a weight used for fusion of the results to ensure an end-to-end manner. Extensive experiments demonstrate that the proposed DualBDNet outperforms the state-of-the-art methods on both synthetic and real noisy images without estimating the noise levels as input.

Keywords

Noise level, Image denoising, Noise reduction, Task analysis, Noise measurement, Estimation, Optimization, Blind image denoising, convolutional neural networks, dual learning, Gaussian noise

Discipline

Information Security

Research Areas

Information Systems and Management

Publication

IEEE Transactions on Multimedia

Volume

23

First Page

2139

Last Page

2152

ISSN

1520-9210

Identifier

10.1109/TMM.2020.3008057

Publisher

Institute of Electrical and Electronics Engineers

Additional URL

https://doi.org/10.1109/TMM.2020.3008057

This document is currently not available here.

Share

COinS