Blur kernel estimation via salient edges and low rank prior for blind image deblurring
作者：
Highlights：
•
• We propose the low rank prior with salient edge selection for blind image deblurring.
• We analyze how the low rank prior helps blur kernel estimation in detail.
• We extend the proposed method and show its effectiveness on nonuniform deblurring.
• We discuss the limitations of the proposed algorithm.
• We evaluate our method on both synthetic and real-world images.
摘要
•We propose the low rank prior with salient edge selection for blind image deblurring.•We analyze how the low rank prior helps blur kernel estimation in detail.•We extend the proposed method and show its effectiveness on nonuniform deblurring.•We discuss the limitations of the proposed algorithm.•We evaluate our method on both synthetic and real-world images.
论文关键词：Blind image deblurring,Low rank prior,Salient edges,Kernel estimation,Image restoration
论文评审过程：Received 19 December 2016, Revised 14 July 2017, Accepted 16 July 2017, Available online 27 July 2017, Version of Record 4 August 2017.
论文官网地址：https://doi.org/10.1016/j.image.2017.07.004
