English

Image Denoising with Graph-Convolutional Neural Networks

Image and Video Processing 2019-05-30 v1 Computer Vision and Pattern Recognition

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.

Keywords

Cite

@article{arxiv.1905.12281,
  title  = {Image Denoising with Graph-Convolutional Neural Networks},
  author = {Diego Valsesia and Giulia Fracastoro and Enrico Magli},
  journal= {arXiv preprint arXiv:1905.12281},
  year   = {2019}
}

Comments

IEEE International Conference on Image Processing (ICIP) 2019

R2 v1 2026-06-23T09:31:04.913Z