A smarter exemplar-based inpainting algorithm using local and global heuristics for more geometric coherence
Résumé
In this paper, we propose two major improvements to the exemplar-based image inpainting algorithm, initially formu-lated by Criminisi et al. [1]. First, we introduce a structure-tensor-based data-term for a better selection of pixel candi-dates to fill in based on priority. Then, we propose a new lookup heuristic in order to locate the best source patches to copy/paste to these targeted points. These two contributions clearly make the inpainting algorithm reconstruct more geo-metrically coherent images, as well as speed up the process drastically. We illustrate the great performances of our ap-proach compared to existing state-of-the-art methods.
Origine : Fichiers produits par l'(les) auteur(s)
Loading...