A Simple and Robust Deep Convolutional Approach to Blind Image Denoising

Hengyuan Zhao, Wenze Shao, Bingkun Bao, Haibo Li; Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), 2019, pp. 0-0

Abstract


Image denoising, particularly Gaussian denoising, has achieved continuous success in the past decades. Although deep convolutional neural networks (CNNs) are also shown leading high-performance in Gaussian denoising just as in many other computer vision tasks, they are not competitive at all on real noisy photographs to representative classical methods such as BM3D and WNNM. In this paper, a simple yet robust method is proposed to improve the effectiveness and practicability of deep denoising models. In view of the difference between real-world noise in camera systems and additive white Gaussian noise (AWGN), the model learning has exploited clean-noisy image pairs newly produced built on a generalized signal dependent noise model. During the model inference, the proposed denoising model is not only blind to the noise type but also to the noise level. Meanwhile, in order to separate the noise from image content as full as possible, a new convolutional architecture is advocated for such a blind denoising task where a kind of lifting residual modules is specifically proposed for discriminative feature extraction. Experimental results on both simulated and real noisy images demonstrate that the proposed blind denoiser achieves fairly competitive or even better performance than state-of-the-art algorithms in terms of both quantitative and qualitative assessment. The codes of the proposed method are available at https://github.com/zhaohengyuan1/SDNet.

Related Material


[pdf]
[bibtex]
@InProceedings{Zhao_2019_ICCV,
author = {Zhao, Hengyuan and Shao, Wenze and Bao, Bingkun and Li, Haibo},
title = {A Simple and Robust Deep Convolutional Approach to Blind Image Denoising},
booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) Workshops},
month = {Oct},
year = {2019}
}