Deep Graph-Convolutional Image Denoising

Abstract

Non-local self-similarity is well-known to be an effective prior for the image denoising problem. However, little work has been done to incorporate it in convolutional neural networks, which surpass non-local model-based methods despite only exploiting local information. In this paper, we propose a novel end-to-end trainable neural network architecture employing layers based on graph convolution operations, thereby creating neurons with non-local receptive fields. The graph convolution operation generalizes the classic convolution to arbitrary graphs. In this work, the graph is dynamically computed from similarities among the hidden features of the network, so that the powerful representation learning capabilities of the network are exploited to uncover self-similar patterns. We introduce a lightweight Edge-Conditioned Convolution which addresses vanishing gradient and over-parameterization issues of this particular graph convolution. Extensive experiments show state-of-the-art performance with improved qualitative and quantitative results on both synthetic Gaussian noise and real noise.

References in corpus (2)

• Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
• Deep Convolutional Networks on Graph-Structured Data

Cited by in corpus (11)

• Cross-Scale Internal Graph Neural Network for Image Super-Resolution
• Deep Learning Methods For Synthetic Aperture Radar Image Despeckling: An Overview Of Trends And Perspectives
• Coupling Model-Driven and Data-Driven Methods for Remote Sensing Image Restoration and Fusion
• CDLNet: Noise-Adaptive Convolutional Dictionary Learning Network for Blind Denoising and Demosaicing
• Graph Signal Processing for Geometric Data and Beyond: Theory and Applications
• Polynomial graph filter of multiple shifts and distributed implementation of inverse filtering
• Deep Learning strategies for ProtoDUNE raw data denoising
• Learning Frequency-aware Dynamic Network for Efficient Super-Resolution
• Reinforcement Learning of Self Enhancing Camera Image and Signal Processing
• Deep Contrastive Patch-Based Subspace Learning for Camera Image Signal Processing
• Fine-Grained Named Entity Typing over Distantly Supervised Data Based on Refined Representations