.png){kind=icon}
返回
Blind deblurring with patch-wise second-order gradient prior
.png){kind=icon}
PRE
AI
DOI：10.1016/j.image.2022.116781.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
The patch-based image priors have been successfully applied to blind image deblurring algorithms. But those priors are time-consuming since too many non-linear operators are involved. However, the solving of these prior needs to use nonlinear operators that greatly decrease the computational efficiency. Proposed in this study is a simply patch-wise image prior that uses non-overlapped local patches to compute the local maximal second-order gradient of an image. We find that the values of the patch-wise second-order gradient (PSG) of an image decrease with the motion blur process. A new optimization algorithm is proposed by combining L-1 regularized PSG with the maximum posterior probability. Besides, kernel similarity constraint is employed to control the iteration times to reduce the computational costs. Comparative experiments on mainstream datasets show that the results of the presented algorithm are generally better than those of other algorithms on both quantitative contrast and visual contrast.
Keyword:
Motion deblurring
Second-order gradient
Kernel similarity
Blind deconvolution
Local image patches
期刊
S
IF:
2.7
论文数:
2.8K
被引数:
4.2K
机构
引用论文
Religiosidade como possível fator de proteção do “binge drinking” por escolares de 12 anos de idade: um estudo de base populacional宗教性作为12岁学龄儿童“binge drinking”的潜在保护性因素：一项基于人群的研究
OAAI
OAAI分享收藏分享收藏Thermal Case Study of Cilia Actuated Transport of Radiated Blood-Based Ternary Nanofluid under the Action of Tilted Magnetic Field.png)
Coatings
OAAI
CoatingsIF0
OAAI分享收藏分享收藏
查看更多内容