Image completion with global structure and weighted nuclear norm regularization

Image completion with global structure and weighted nuclear norm regularization

Zhang, Mingli and Desrosiers, Christian

Proceedings of the International Joint Conference on Neural Networks 2017

Abstract : Structure and nonlocal patch similarity have been used successfully to enhance the performance of image restoration. However, these techniques can often remove textures and edges, or introduce artifacts. In this paper, we propose a novel image completion method that leverages the redundancy of nonlocal image patches via the low-rank regularization of similar patch groups. The textures and edges in these patches are preserved using an adaptive regularization technique based on the weighted nuclear norm. Furthermore, a new global structure regularization strategy, imposing ℓ1-norm sparsity on the image’s high-frequency residual component, is presented to recover missing pixels while preserving structural information in the image. An efficient optimization technique, based on the Alternating Direction Method of Multipliers (ADMM) algorithm, is used to solve the proposed model. Experimental results show our method to outperform state-of-the-art image completion approaches, for various text-corrupted images and different ratios of missing pixels.