Abstract
Recovering an image from a noisy observation is a key problem in signal processing. Recently, it has been shown that data-driven approaches employing convolutional neural networks can outperform classical model-based techniques, because they can capture more powerful and discriminative features. However, since these methods are based on convolutional operations, they are only capable of exploiting local similarities without taking into account non-local self-similarities. In this paper we propose a convolutional neural network that employs graph-convolutional layers in order to exploit both local and non-local similarities. The graph-convolutional layers dynamically construct neighborhoods in the feature space to detect latent correlations in the feature maps produced by the hidden layers. The experimental results show that the proposed architecture outperforms classical convolutional neural networks for the denoising task.
Abstract (translated)
从噪声观测中恢复图像是信号处理中的一个关键问题。近年来,研究表明,采用卷积神经网络的数据驱动方法可以优于传统的基于模型的技术,因为它们可以捕获更强大和更具辨别力的特征。然而,由于这些方法是基于卷积运算的,它们只能利用局部相似性,而不考虑非局部自相似性。本文提出了一种利用图卷积层的卷积神经网络,利用图卷积层的局部相似性和非局部相似性。图卷积层在特征空间中动态构建邻域,以检测隐藏层生成的特征图中的潜在相关性。实验结果表明,该结构在去噪方面优于传统的卷积神经网络。
URL
https://arxiv.org/abs/1905.12281