Low-rank matrix approximation has been successfully applied to numerous vision problems in recent years. In this paper, we propose a novel low-rank prior for blind image deblurring. Our key observation is that directly applying a simple low-rank model to a blurry input image significantly reduces the blur even without using any kernel information, while preserving important edge information. The same model can be used to reduce blur in the gradient map of a blurry input. Based on these properties, we introduce an enhanced prior for image deblurring by combining the low rank prior of similar patches from both the blurry image and its gradient map. We employ a weighted nuclear norm minimization method to further enhance the effectiveness of low-rank prior for image deblurring, by retaining the dominant edges and eliminating fine texture and slight edges in intermediate images, allowing for better kernel estimation. In addition, we evaluate the proposed enhanced low-rank prior for both the uniform and the non-uniform deblurring. Quantitative and qualitative experimental evaluations demonstrate that the proposed algorithm performs favorably against the state-of-the-art deblurring methods.
Bibliographical noteFunding Information:
This work was supported in part by the National High-Tech Research and Development Program of China under Grant 2013CB329305, in part by the National Basic Research Program of China under Grant 2013CB329305, in part by the National Natural Science Foundation of China under Grant 61422213, Grant 61271093, and Grant 61402467, and in part by the Chinese Academy of Sciences through the Strategic Priority Research Program under Grant XDA06010701. The work of X. Guo was supported by the Chinese Academy of Sciences within the Institute Information Engineering through the Excellent Young Talent Programme. The work of M.-H. Yang was supported in part by the National Science Foundation (NSF) through the CAREER Program under Grant 1149783 and in part by NSF Grant 1152576 and in part by NSF within the Division of Information and Intelligent Systems through a Gift from Adobe. The associate editor coordinating the review of this manuscript and approving it for publication was Dr. Christopher Wyatt.
All Science Journal Classification (ASJC) codes
- Computer Graphics and Computer-Aided Design