Space-variant blur kernel estimation and image deblurring through kernel clustering
作者：
Highlights：
• A space-variant image deblurring method is presented.
• An input image is divided into small overlapping patches, for which the blur kernel is estimated.
• Blur kernels are then clustered to determine main kernel groups and eliminate unreliable ones.
• The kernel clustering process at the end results in accurate kernels.
• The input image is deblurred with each kernel; deblurred images are fused to produce final result.
摘要
•A space-variant image deblurring method is presented.•An input image is divided into small overlapping patches, for which the blur kernel is estimated.•Blur kernels are then clustered to determine main kernel groups and eliminate unreliable ones.•The kernel clustering process at the end results in accurate kernels.•The input image is deblurred with each kernel; deblurred images are fused to produce final result.
论文关键词：Space-variant image deblurring,Space-variant PSF estimation,Image fusion
论文评审过程：Received 23 October 2018, Revised 16 April 2019, Accepted 16 April 2019, Available online 27 April 2019, Version of Record 3 May 2019.
论文官网地址：https://doi.org/10.1016/j.image.2019.04.014
