Nonlocality-Reinforced Convolutional Neural Networks for Image Denoising

Abstract

We introduce a paradigm for nonlocal sparsity reinforced deep convolutional neural network denoising. It is a combination of a local multiscale denoising by a convolutional neural network (CNN) based denoiser and a nonlocal denoising based on a nonlocal filter (NLF) exploiting the mutual similarities between groups of patches. CNN models are leveraged with noise levels that progressively decrease at every iteration of our framework, while their output is regularized by a nonlocal prior implicit within the NLF. Unlike complicated neural networks that embed the nonlocality prior within the layers of the network, our framework is modular, it uses standard pre-trained CNNs together with standard nonlocal filters. An instance of the proposed framework, called NN3D, is evaluated over large grayscale image datasets showing state-of-the-art performance.

arXiv commentAccepted for publication in IEEE SPL

References in corpus (3)

• Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising
• Trainable Nonlinear Reaction Diffusion: A Flexible Framework for Fast and Effective Image Restoration
• Single Image Super-Resolution based on Wiener Filter in Similarity Domain

Cited by in corpus (11)

• Deep Graph-Convolutional Image Denoising
• Deep Learning Methods For Synthetic Aperture Radar Image Despeckling: An Overview Of Trends And Perspectives
• Optical Fringe Patterns Filtering Based on Multi-Stage Convolution Neural Network
• Neural Nearest Neighbors Networks
• Non-Local Video Denoising by CNN
• Fast, nonlocal and neural: a lightweight high quality solution to image denoising
• Deep Learning on Image Denoising: An overview
• PNEN: Pyramid Non-Local Enhanced Networks
• AccessFixer: Enhancing GUI Accessibility for Low Vision Users With R-GCN Model
• Removing Multi-frame Gaussian Noise by Combining Patch-based Filters with Optical Flow
• Fully Convolutional Pixel Adaptive Image Denoiser