Hierarchical dense recursive network for image super-resolution

作者：

Highlights：

• Hierarchical dense connection provides rich linking ways for feature representation.

• Reasonable design and parameter sharing contribute for light-weight SR model.

• Global feature fusion promotes fine residual learning.

摘要

•Hierarchical dense connection provides rich linking ways for feature representation.•Reasonable design and parameter sharing contribute for light-weight SR model.•Global feature fusion promotes fine residual learning.

论文关键词：Super-resolution,Hierarchical dense connection,Global feature fusion,Recursive network,Multi-scale

论文评审过程：Received 6 June 2019, Revised 17 March 2020, Accepted 23 May 2020, Available online 26 May 2020, Version of Record 5 June 2020.

论文官网地址：https://doi.org/10.1016/j.patcog.2020.107475