Enhanced CNN for image denoising

Abstract

Owing to flexible architectures of deep convolutional neural networks (CNNs), CNNs are successfully used for image denoising. However, they suffer from the following drawbacks: (i) deep network architecture is very difficult to train. (ii) Deeper networks face the challenge of performance saturation. In this study, the authors propose a novel method called enhanced convolutional neural denoising network (ECNDNet). Specifically, they use residual learning and batch normalisation techniques to address the problem of training difficulties and accelerate the convergence of the network. In addition, dilated convolutions are used in the proposed network to enlarge the context information and reduce the computational cost. Extensive experiments demonstrate that the ECNDNet outperforms the state-of-the-art methods for image denoising.

arXiv commentCAAI Transactions on Intelligence Technology[J], 2019

References in corpus (11)

• Adam: A Method for Stochastic Optimization
• Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
• Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising
• FFDNet: Toward a Fast and Flexible Solution for CNN based Image Denoising
• Multi-Scale Context Aggregation by Dilated Convolutions
• Trainable Nonlinear Reaction Diffusion: A Flexible Framework for Fast and Effective Image Restoration
• Medical image denoising using convolutional denoising autoencoders
• A Cascaded Convolutional Neural Network for X-ray Low-dose CT Image Denoising
• Multi-level Wavelet-CNN for Image Restoration
• Block-Matching Convolutional Neural Network for Image Denoising
• Deep Learning for Image Denoising: A Survey

Cited by in corpus (12)

• Deep Learning on Image Denoising: An overview
• Designing and Training of A Dual CNN for Image Denoising
• NeighCNN: A CNN based SAR Speckle Reduction using Feature preserving Loss Function
• Single Image Brightening via Multi-Scale Exposure Fusion with Hybrid Learning
• Evaluating Similitude and Robustness of Deep Image Denoising Models via Adversarial Attack
• Automatic artifact removal of resting-state fMRI with Deep Neural Networks
• Lightweight image super-resolution with enhanced CNN
• CASSOD-Net: Cascaded and Separable Structures of Dilated Convolution for Embedded Vision Systems and Applications
• Blind Image Super-Resolution with Spatial Context Hallucination
• Exposure Interpolation by Combining Model-driven and Data-driven Methods
• Single image dehazing via combining the prior knowledge and CNNs
• Recovery of surfaces and functions in high dimensions: sampling theory and links to neural networks