Single image super‐resolution based on progressive fusion of orientation‐aware features

作者：

Highlights：

• We combined 1D and 2D convolutional kernels to extract orientation-aware features.

• We employed a channel attention mechanism to adaptively select informative orientation-aware features.

• Progressive feature fusion scheme is proposed to fuse hierarchical features.

摘要

•We combined 1D and 2D convolutional kernels to extract orientation-aware features.•We employed a channel attention mechanism to adaptively select informative orientation-aware features.•Progressive feature fusion scheme is proposed to fuse hierarchical features.

论文关键词：Single image super-resolution,Channel attention,Orientation-aware,Feature extraction,Feature fusion

论文评审过程：Received 17 August 2020, Revised 17 May 2022, Accepted 6 September 2022, Available online 10 September 2022, Version of Record 20 September 2022.

论文官网地址：https://doi.org/10.1016/j.patcog.2022.109038