Abstract
Atmospheric turbulence significantly degrades image quality. A blind image deblurring algorithm is needed, and a favorable image prior is the key to solving this problem. However, the general sparse priors support blurry images instead of explicit images, so the details of the restored images are lost. The recently developed priors are non-convex, resulting in complex and heuristic optimization. To handle these problems, we first propose a convex image prior; namely, maximizing L1 regularization (ML1). Benefiting from the symmetrybetween ML1 and L1 regularization, the ML1 supports clear images and preserves the image edges better. Then, a novel soft suppression strategy is designed for the deblurring algorithm to inhibit artifacts. A coarse-to-fine scheme and a non-blind algorithm are also constructed. For qualitative comparison, a turbulent blur dataset is built. Experiments on this dataset and real images demonstrate that the proposed method is superior to other state-of-the-art methods in blindly recovering turbulent images.
Highlights
As an essential tool for improving image quality, image deblurring has received considerable attention
maximizing L1 regularization (ML1) prior, we propose a deblurring algorithm with a soft suppression strategy, termed suppressed projected alternating minimization (SPAM). (3) To assess the effectiveness of the proposed method, we build a turbulent blur images dataset
We proposed a maximizing L1 regularization prior, which is motivated by effectively supporting sharp latent images instead of turbulence blurry images
Summary
As an essential tool for improving image quality, image deblurring has received considerable attention. Blind image deblurring involves estimating a latent sharp image o and a blur kernel h, with a blurry input image g. The blurring process is modeled as: g = o∗h+n (1). Where ∗ represents the convolution operator and n denotes the additional noise. Involving an infinite number of solutions, this problem is strongly ill-posed. To regularize Problem (1), various image priors [1,2,3,4,5,6,7,8,9,10] have been proposed. The simplest is a Gaussian prior based on the natural image obeying a Gaussian distribution [1,2]
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
