Deep Learning on Image Denoising: An overview

Abstract

Deep learning techniques have received much attention in the area of image denoising. However, there are substantial differences in the various types of deep learning methods dealing with image denoising. Specifically, discriminative learning based on deep learning can ably address the issue of Gaussian noise. Optimization models based on deep learning are effective in estimating the real noise. However, there has thus far been little related research to summarize the different deep learning techniques for image denoising. In this paper, we offer a comparative study of deep techniques in image denoising. We first classify the deep convolutional neural networks (CNNs) for additive white noisy images; the deep CNNs for real noisy images; the deep CNNs for blind denoising and the deep CNNs for hybrid noisy images, which represents the combination of noisy, blurred and low-resolution images. Then, we analyze the motivations and principles of the different types of deep learning methods. Next, we compare the state-of-the-art methods on public denoising datasets in terms of quantitative and qualitative analysis. Finally, we point out some potential challenges and directions of future research.

References in corpus (44)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Deep Learning in Neural Networks: An Overview
• A Survey on Deep Learning in Medical Image Analysis
• Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising
• Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
• Deep Convolutional Neural Network for Inverse Problems in Imaging
• Learning Face Representation from Scratch
• Trainable Nonlinear Reaction Diffusion: A Flexible Framework for Fast and Effective Image Restoration
• Image Restoration Using Very Deep Convolutional Encoder-Decoder Networks with Symmetric Skip Connections
• cuDNN: Efficient Primitives for Deep Learning
• Opening the Black Box of Deep Neural Networks via Information
• Hyperspectral Image Denoising Employing a Spatial-Spectral Deep Residual Convolutional Neural Network
• More Bang for Your Buck: Improved use of GPU Nodes for GROMACS 2018
• Batch Renormalization: Towards Reducing Minibatch Dependence in Batch-Normalized Models
• Variational Denoising Network: Toward Blind Noise Modeling and Removal
• Enhanced CNN for image denoising
• Real-world Noisy Image Denoising: A New Benchmark
• External Prior Guided Internal Prior Learning for Real-World Noisy Image Denoising
• Nonlocality-Reinforced Convolutional Neural Networks for Image Denoising
• Iterative Joint Image Demosaicking and Denoising using a Residual Denoising Network
• Deep Mean-Shift Priors for Image Restoration
• Light Field Denoising via Anisotropic Parallax Analysis in a CNN Framework
• Three-dimensional Optical Coherence Tomography Image Denoising through Multi-input Fully-Convolutional Networks
• Correction by Projection: Denoising Images with Generative Adversarial Networks
• Multi-Kernel Prediction Networks for Denoising of Burst Images
• Learning Deformable Kernels for Image and Video Denoising
• Non-Local Video Denoising by CNN
• Generating Training Data for Denoising Real RGB Images via Camera Pipeline Simulation
• When Image Denoising Meets High-Level Vision Tasks: A Deep Learning Approach
• Block-Matching Convolutional Neural Network for Image Denoising
• Recovering Loss to Followup Information Using Denoising Autoencoders
• Wide Inference Network for Image Denoising via Learning Pixel-distribution Prior
• Interactive Multi-Dimension Modulation with Dynamic Controllable Residual Learning for Image Restoration
• Chaining Identity Mapping Modules for Image Denoising
• Unsupervised Image Noise Modeling with Self-Consistent GAN
• First image then video: A two-stage network for spatiotemporal video denoising
• Designing and Training of A Dual CNN for Image Denoising
• GAN2GAN: Generative Noise Learning for Blind Denoising with Single Noisy Images
• End-to-End Denoising of Dark Burst Images Using Recurrent Fully Convolutional Networks
• Learning Deep Gradient Descent Optimization for Image Deconvolution
• Basis Prediction Networks for Effective Burst Denoising with Large Kernels
• Fast Spatio-Temporal Residual Network for Video Super-Resolution
• Image Denoising and Super-Resolution using Residual Learning of Deep Convolutional Network
• Self-supervised Dynamic CT Perfusion Image Denoising with Deep Neural Networks

Cited by in corpus (6)

• Review: Deep Learning in Electron Microscopy
• Developing and Evaluating Deep Neural Network-based Denoising for Nanoparticle TEM Images with Ultra-low Signal-to-Noise
• Generalized Octave Convolutions for Learned Multi-Frequency Image Compression
• Designing and Training of A Dual CNN for Image Denoising
• An Encoder-Decoder CNN for Hair Removal in Dermoscopic Images
• Asymmetric CNN for image super-resolution