Deblurring Turbulent Images via Maximizing L1 Regularization

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.

A Shearlets-Based Method for Rain Removal from Single Images

This work focuses on the problem of rain removal from a single image. The directional multilevel system, Shearlets, is used to describe the intrinsic directional and structure sparse priors of rain streaks and the background layer. In this paper, a Shearlets-based convex rain removal model is proposed, which involves three sparse regularizers: including the sparse regularizer of rain streaks and two sparse regularizers of the Shearlets transform of background layer in the rain drops’ direction and the Shearlets transform of rain streaks in the perpendicular direction. The split Bregman algorithm is utilized to solve the proposed convex optimization model, which ensures the global optimal solution. Comparison tests with three state-of-the-art methods are implemented on synthetic and real rainy images, which suggests that the proposed method is efficient both in rain removal and details preservation of the background layer.