Video super resolution based on non-local regularization and reliable motion estimation

作者：

Highlights：

• Adaptive anti-aliasing and multi-lateral filters are used to regularize the motion estimation.

• Non-local prior is adopted for image reconstruction to reduce artifacts.

• The proposed method exhibits self-adaptive capability because all prior knowledge is derived from the recovered image itself.

摘要

Highlights•Adaptive anti-aliasing and multi-lateral filters are used to regularize the motion estimation.•Non-local prior is adopted for image reconstruction to reduce artifacts.•The proposed method exhibits self-adaptive capability because all prior knowledge is derived from the recovered image itself.

论文关键词：Super-resolution,Non-local regularization,Motion estimation,Blur kernel estimation

论文评审过程：Received 4 August 2013, Revised 14 November 2013, Accepted 6 January 2014, Available online 28 January 2014.

论文官网地址：https://doi.org/10.1016/j.image.2014.01.002