Adaptive feature denoising based deep convolutional network for single image super-resolution

作者：

Highlights：

• We propose a novel lightweight adaptive soft thresholding (AST) mechanism to perform the specific feature recalibration (FMR) for single image super-resolution (SISR).

• We propose an adaptive Feature Denoising Super-Resolution (FDSR) network by embedding the proposed AST modules into the classic EDSR architecture.

摘要

•We propose a novel lightweight adaptive soft thresholding (AST) mechanism to perform the specific feature recalibration (FMR) for single image super-resolution (SISR).•We propose an adaptive Feature Denoising Super-Resolution (FDSR) network by embedding the proposed AST modules into the classic EDSR architecture.

论文关键词：Super-resolution,Feature denoising,Deep learning,Soft thresholding

论文评审过程：Received 26 November 2021, Revised 10 July 2022, Accepted 27 July 2022, Available online 4 August 2022, Version of Record 10 August 2022.

论文官网地址：https://doi.org/10.1016/j.cviu.2022.103518