Layered input GradiNet for image denoising

作者：

Highlights：

• A layered input gradient network (LIGN) based on a dual U-Net for high-quality image denoising is proposed.

• Layered input and sharpening loss greatly improve the perceptual quality of the denoised image.

• Multi-scale feature extraction block can capture more semantic information.

• LIGN achieves the SoTA performance compared with the latest methods on synthetic and real noise datasets.

摘要

•A layered input gradient network (LIGN) based on a dual U-Net for high-quality image denoising is proposed.•Layered input and sharpening loss greatly improve the perceptual quality of the denoised image.•Multi-scale feature extraction block can capture more semantic information.•LIGN achieves the SoTA performance compared with the latest methods on synthetic and real noise datasets.

论文关键词：Image denoising,Deep neural network,Gradient fusion,Multiscale feature,Layered input,Sharpening loss

论文评审过程：Received 10 March 2022, Revised 27 July 2022, Accepted 30 July 2022, Available online 4 August 2022, Version of Record 23 August 2022.

论文官网地址：https://doi.org/10.1016/j.knosys.2022.109587