A novel deep neural network for noise removal from underwater image

作者：

Highlights：

• Proposing a novel deep neural network for noise removal from underwater image.

• Introducing the self-attention mechanism in the generative network can generate a denoised image with fine details, thereby improving the effect of image denoising.

• The proposed network has the good ability to remove the spot noise from underwater images while preserving sharp edge and fine details.

摘要

•Proposing a novel deep neural network for noise removal from underwater image.•Introducing the self-attention mechanism in the generative network can generate a denoised image with fine details, thereby improving the effect of image denoising.•The proposed network has the good ability to remove the spot noise from underwater images while preserving sharp edge and fine details.

论文关键词：Underwater image,Noise removal,Generative adversarial network,Self-attention,Spectral normalization

论文评审过程：Received 25 October 2019, Revised 15 May 2020, Accepted 11 June 2020, Available online 18 June 2020, Version of Record 20 June 2020.

论文官网地址：https://doi.org/10.1016/j.image.2020.115921