Deep learning on image denoising: an overview
From MaRDI portal
Publication:2057732
DOI10.1016/J.NEUNET.2020.07.025zbMATH Open1475.68324arXiv1912.13171OpenAlexW3047011367WikidataQ98629971 ScholiaQ98629971MaRDI QIDQ2057732FDOQ2057732
Authors: Chunwei Tian, Lunke Fei, Wenxian Zheng, Yong Xu, Wangmeng Zuo, Chia-Wen Lin 
Publication date: 7 December 2021
Published in: Neural Networks (Search for Journal in Brave)
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.
Full work available at URL: https://arxiv.org/abs/1912.13171
Recommendations
- A review of image denoising methods
- Mathematical and deep learning methods in image inverse problems
- Rate-optimal denoising with deep neural networks
- A summary review of the methods for image super-resolution reconstruction based on deep learning
- Review on deep learning based image super-resolution restoration algorithms
Artificial neural networks and deep learning (68T07) Image processing (compression, reconstruction, etc.) in information and communication theory (94A08)
Cites Work
- $rm K$-SVD: An Algorithm for Designing Overcomplete Dictionaries for Sparse Representation
- Reducing the Dimensionality of Data with Neural Networks
- Nonlocally Centralized Sparse Representation for Image Restoration
- An Iterative Regularization Method for Total Variation-Based Image Restoration
- Extended tanh-function method and its applications to nonlinear equations
- Neocognition: A self-organizing neural network model for a mechanism of pattern recognition unaffected by shift in position
- FSIM: A Feature Similarity Index for Image Quality Assessment
- A Fast Learning Algorithm for Deep Belief Nets
- Large-scale machine learning with stochastic gradient descent
- Beyond sparsity: the role of \(L_{1}\)-optimizer in pattern classification
- Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising
- Deep Convolutional Neural Network for Inverse Problems in Imaging
- Deep convolutional framelets: a general deep learning framework for inverse problems
- Gradient Histogram Estimation and Preservation for Texture Enhanced Image Denoising
- Image restoration using a multilayer perceptron with a multilevel sigmoidal function
- Robust learning with imperfect privileged information
- Similarity and diversity induced paired projection for cross-modal retrieval
- External Prior Guided Internal Prior Learning for Real-World Noisy Image Denoising
- Class-Aware Fully Convolutional Gaussian and Poisson Denoising
- Waterloo Exploration Database: New Challenges for Image Quality Assessment Models
- Single Image Deraining Using Bilateral Recurrent Network
- Iterative Joint Image Demosaicking and Denoising Using a Residual Denoising Network
- Low-Light Image Enhancement via a Deep Hybrid Network
Cited In (10)
- An hybrid denoising algorithm based on directional wavelet packets
- A review of image denoising methods
- Influence of image data set noise on classification with a convolutional network
- A novel method of image denoising based on 2D dual-tree DWT and SWT
- Generative adversarial networks for robust cryo-EM image denoising
- Image Denoising: The Deep Learning Revolution and Beyond—A Survey Paper
- A review on denoising
- Consensus guided incomplete multi-view spectral clustering
- MFLP-PINN: a physics-informed neural network for multiaxial fatigue life prediction
- Learnable nonlocal self-similarity of deep features for image denoising
Uses Software
This page was built for publication: Deep learning on image denoising: an overview
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2057732)
