A new nonlocal variational bi-regularized image restoration model via split Bregman method

Abstract

In this paper, we propose a new variational model for image restoration by incorporating a nonlocal TV regularizer and a nonlocal Laplacian regularizer on the image. The two regularizing terms make use of nonlocal comparisons between pairs of patches in the image. The new model can be seen as a nonlocal version of the CEP- L 2 model. Subsequently, an algorithm combining the alternating directional minimization and the split Bregman iteration is presented to solve the new model. Numerical results verified that the proposed method has better performance for image restoration than CEP- L 2 model, especially for low noised images.