Bilevel learning approach for nonlocal p-Laplacien image deblurring with variable weights parameter w(x)

This manuscript introduces an innovative bilevel optimization approach designed to improve the deblurring process by incorporating a nonlocal p-Laplacien model with variable weights. The study includes a theoretical analysis to examine the model’s solution, and an effective algorithm is devised for computing the pristine image, incorporating the learning of parameters associated with weights and nonlocal regularization terms. By carefully selecting these parameters, the suggested nonlocal deblurring model demonstrates superior effectiveness and performance when compared to other existing models.