English

Enhanced CNN for image denoising

Computer Vision and Pattern Recognition 2019-03-05 v4

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.

Keywords

Cite

@article{arxiv.1810.11834,
  title  = {Enhanced CNN for image denoising},
  author = {Chunwei Tian and Yong Xu and Lunke Fei and Junqian Wang and Jie Wen and Nan Luo},
  journal= {arXiv preprint arXiv:1810.11834},
  year   = {2019}
}

Comments

CAAI Transactions on Intelligence Technology[J], 2019

R2 v1 2026-06-23T04:55:00.466Z