A nonsubsampled countourlet transform based CNN for real image denoising

作者：

Highlights：

• Building a novel NSCT based CNN model to improve the image denoising performance with better compromise between performance and computation time cost.

• The proposed method can deal with noise from real images, and preserve details information.

摘要

•Building a novel NSCT based CNN model to improve the image denoising performance with better compromise between performance and computation time cost.•The proposed method can deal with noise from real images, and preserve details information.

论文关键词：Nonsubsampled countourlet transform,Convolutional Neural Networks,Image denoising,Gaussian noise

论文评审过程：Received 23 April 2019, Revised 29 September 2019, Accepted 29 November 2019, Available online 6 December 2019, Version of Record 19 December 2019.

论文官网地址：https://doi.org/10.1016/j.image.2019.115727