Image Denoising with Graph-Convolutional Neural Networks
This addresses image denoising for signal processing applications, but it is incremental as it builds on existing data-driven approaches.
The paper tackled image denoising by proposing a graph-convolutional neural network to exploit both local and non-local similarities, and the results showed it outperforms classical convolutional neural networks for this task.
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.