Graph-based Image Inpainting

The project goal was to explore the applications of spectral graph theory to address the inpainting problem of large missing chunks. We used a non-local patch graph representation of the image and proposed a structure detector which leverages the graph representation and influences the fill-order of our exemplar-based algorithm. Our method achieved state-of-the-art performances.


Directeur(s):
Vandergheynst, Pierre
Perraudin, Nathanaël
Paratte, Johann
Schoenenberger, Yann Mikaël
Année
2014
Mots-clefs:
Laboratoires:




 Notice créée le 2016-04-13, modifiée le 2018-10-01

n/a:
Télécharger le documentPDF
Lien externe:
Télécharger le documentURL
Évaluer ce document:

Rate this document:
1
2
3
 
(Pas encore évalué)