# Image Denoising with Graph-Convolutional Neural Networks

## TL;DR

This paper introduces a graph-convolutional neural network for image denoising that captures both local and non-local similarities, outperforming traditional CNNs in experimental tests.

## Contribution

It proposes a novel CNN architecture with graph-convolutional layers that dynamically model non-local feature correlations for improved denoising.

## Key findings

- Outperforms classical CNNs in image denoising tasks.
- Effectively captures non-local self-similarities in images.
- Demonstrates superior denoising quality in experiments.

## 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.