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.


Advisor(s):
Vandergheynst, Pierre
Perraudin, Nathanaël
Paratte, Johann
Schoenenberger, Yann Mikaël
Year:
2014
Keywords:
Laboratories:




 Record created 2016-04-13, last modified 2018-09-25

n/a:
Download fulltextPDF
External link:
Download fulltextURL
Rate this document:

Rate this document:
1
2
3
 
(Not yet reviewed)