Kernel-attended residual network for single image super-resolution

作者：

Highlights：

• We propose the kernel-attended residual network for image super-resolution.

• We propose multi-channel fusion block (MCFB) and kernel-attended block (KAB).

• We propose spatial feature recalibration block (SFRB).

摘要

•We propose the kernel-attended residual network for image super-resolution.•We propose multi-channel fusion block (MCFB) and kernel-attended block (KAB).•We propose spatial feature recalibration block (SFRB).

论文关键词：Single image super-resolution,Convolution neural network,Deep learning,Neural network,Attention mechanism,Learning-based method,Kernel attention

论文评审过程：Received 15 September 2020, Revised 27 November 2020, Accepted 8 December 2020, Available online 18 December 2020, Version of Record 31 December 2020.

论文官网地址：https://doi.org/10.1016/j.knosys.2020.106663