Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising
Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising
复制标题
超越高斯降噪器：用于图像降噪的深度 CNN 残差学习
DOI：
10.1109/tip.2017.2662206
复制
发表时间：
2017-07-01
影响因子：
10.6
通讯作者：
Zhang, Lei
中科院分区：
文献类型：
--
作者：
Zhang, Kai;Zuo, Wangmeng;Zhang, Lei
判别模型学习用于图像去噪，由于其良好的去噪性能，近年来引起了人们的广泛关注。本文通过研究前馈去噪卷积神经网络(DnCNN)的构造，将深层次的结构、学习算法和正则化方法应用到图像去噪中。具体地说，利用残差学习和批归一化来加快训练过程，提高去噪性能。不同于现有的判别去噪模型通常在一定的噪声水平下对加性高斯白噪声训练特定的模型，我们的DnCNN模型能够处理未知噪声水平的高斯去噪(即盲高斯去噪)。利用残差学习策略，DnCNN隐含地去除了隐含在隐含层中的干净图像。这一特性促使我们训练一个单一的DnCNN模型来处理几种常见的图像去噪任务，如高斯去噪、单图像超分辨率和JPEG图像去块。大量的实验表明，我们的DnCNN模型不仅在几个一般的图像去噪任务中表现出了高效的性能，而且得益于GPU计算而得到了高效的实现。
The discriminative model learning for image denoising has been recently attracting considerable attentions due to its favorable denoising performance. In this paper, we take one step forward by investigating the construction of feed-forward denoising convolutional neural networks (DnCNNs) to embrace the progress in very deep architecture, learning algorithm, and regularization method into image denoising. Specifically, residual learning and batch normalization are utilized to speed up the training process as well as boost the denoising performance. Different from the existing discriminative denoising models which usually train a specific model for additive white Gaussian noise at a certain noise level, our DnCNN model is able to handle Gaussian denoising with unknown noise level (i.e., blind Gaussian denoising). With the residual learning strategy, DnCNN implicitly removes the latent clean image in the hidden layers. This property motivates us to train a single DnCNN model to tackle with several general image denoising tasks, such as Gaussian denoising, single image super-resolution, and JPEG image deblocking. Our extensive experiments demonstrate that our DnCNN model can not only exhibit high effectiveness in several general image denoising tasks, but also be efficiently implemented by benefiting from GPU computing.