Learning nonlocal weights for second-order nonlocal super-resolution

Abstract

This research introduces an enhanced approach for multiframe super-resolution (SR) that incorporates a bilevel optimization technique for learning the space variable weights parameter in the second-order nonlocal term. This novel approach effectively preserves image edges and ensures accurate reconstruction of image textures. The main contributions of this work include the establishment of the existence and uniqueness of the solution within a well-posed framework and a bilevel optimization procedure to compute the weights α. The experimental results demonstrate the efficiency and accuracy of the proposed method compared to existing super-resolution approaches. These findings highlight the practical effectiveness and potential of the proposed approach in real-world applications.

Enhancing deblurring through optimal controlled bilevel with nonlocal weighted model

“…Based on the above works and in order to improve the nonlocal learning operator proposed in [22] and adapet it to deblurring motivations, in this paper, a new approach to improving the deblurring process is introduced. The method involves a novel bilevel optimization procedure that incorporates a variable weights nonlocal model and also a computed regularization parameter.…”