Blind turbulent image deblurring through dual patch-wise pixels prior

Abstract

Deblurring turbulent images is an active topic in image processing and low-level vision research. Existing methods usually use the parametric physical model for nonblind image restoration, which lacks adaptability to different turbulent scenes. To overcome this challenge, a dual patch-wise pixels (DPP) prior is proposed for effective blind deblurring of turbulent images. A DPP-based turbulent image deblurring model was established based on the fact that the value of the DPP decreases through the turbulent blurring process, which has been proven both mathematically and experimentally. To solve the nonlinear DPP in the model, a linear mapping operator was constructed. Additionally, half-quadratic splitting and threshold methods were used to solve the L0 regularization term. Experimental results showed that the proposed algorithm performs well on various types of turbulent scenes as well as real images and outperforms state-ofthe-art algorithms in terms of computational efficiency and effectiveness.