Multi-scale feature selection network for lightweight image super-resolution

Minghong Li, Yuqian Zhao, Fan Zhang, Biao Luo, Chunhua Yang, Weihua Gui, Kan Chang

Abstract: Highlights•The MFSB module is proposed to extract multi-scale features from a coarse-to-fine receptive field level.•The SSM module is designed to well fuse multi-scale features by adjusting the receptive field adaptively.•The CCAM mechanism is built in the SSM to learn the selection weights by considering the global and local inter-channel dependencies.•The proposed MFSN is more efficient and effective than many lightweight CNN-based SR methods.