Multi-layer strategy and reconstruction model with low rank and local rank regularizations for single image super-resolution

作者:

Highlights:

• A multi-layer strategy for single image super-resolution is proposed.

• The local rank transform of image is explored to devise a new regularization term.

• A new model with the low rank and local rank regularizations is proposed.

摘要

•A multi-layer strategy for single image super-resolution is proposed.•The local rank transform of image is explored to devise a new regularization term.•A new model with the low rank and local rank regularizations is proposed.

论文关键词:Single image super-resolution,Low rank,Local rank regularization,Image decomposition,Multi-layer

论文评审过程:Received 7 September 2016, Revised 8 April 2017, Accepted 26 May 2017, Available online 15 June 2017, Version of Record 23 June 2017.

论文官网地址:https://doi.org/10.1016/j.image.2017.05.014