Combining synthesis sparse with analysis sparse for single image super-resolution

作者：

Highlights：

• We first introduce synthesis and analysis sparse coding simultaneously into a training model for single image SR problem.

• The introduction of analysis sparse coding model can reduce the time consumption in reconstruction stage.

• We introduce a linear mapping function to reveal the relationship between them.

• The proposed method can possess competitive performance compared with some state-of-art methods.

摘要

•We first introduce synthesis and analysis sparse coding simultaneously into a training model for single image SR problem.•The introduction of analysis sparse coding model can reduce the time consumption in reconstruction stage.•We introduce a linear mapping function to reveal the relationship between them.•The proposed method can possess competitive performance compared with some state-of-art methods.

论文关键词：Analysis sparse coding,Global and nonlocal optimization,Soft threshold shrinkage,Super-resolution,Synthesis sparse coding

论文评审过程：Received 27 August 2019, Revised 10 January 2020, Accepted 22 January 2020, Available online 8 February 2020, Version of Record 15 February 2020.

论文官网地址：https://doi.org/10.1016/j.image.2020.115805