Detail enhancement of image super-resolution based on detail synthesis

作者：

Highlights：

• A detail-enhancement and super-resolution algorithm based on detail synthesis is proposed.

• It combines local self-similarity search and singular value decomposition of patches together.

• The high-frequency block is reconstructed using effective singular values.

• It improved the facet or line phenomenon on edges and areas that have rich texture.

• The method is also applicable to other super-resolution algorithm in detail enhancement.

摘要

•A detail-enhancement and super-resolution algorithm based on detail synthesis is proposed.•It combines local self-similarity search and singular value decomposition of patches together.•The high-frequency block is reconstructed using effective singular values.•It improved the facet or line phenomenon on edges and areas that have rich texture.•The method is also applicable to other super-resolution algorithm in detail enhancement.

论文关键词：Super resolution,Detail enhancement,Singular value decomposition,Local self-similarity

论文评审过程：Received 14 March 2016, Revised 21 July 2016, Accepted 1 November 2016, Available online 9 November 2016, Version of Record 13 November 2016.

论文官网地址：https://doi.org/10.1016/j.image.2016.11.001