DocumentCode :
249425
Title :
A smarter exemplar-based inpainting algorithm using local and global heuristics for more geometric coherence
Author :
Daisy, M. ; Buyssens, P. ; Tschumperle, D. ; Lezoray, O.
Author_Institution :
GREYC, Univ. de Caen Basse-Normandie, Caen, France
fYear :
2014
fDate :
27-30 Oct. 2014
Firstpage :
4622
Lastpage :
4626
Abstract :
In this paper, we propose two major improvements to the exemplar-based image inpainting algorithm, initially formulated by Criminisi et al. [1]. First, we introduce a structure-tensor-based data-term for a better selection of pixel candidates 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 geometrically coherent images, as well as speed up the process drastically. We illustrate the great performances of our approach compared to existing state-of-the-art methods.
Keywords :
coherence; image restoration; exemplar-based inpainting algorithm; geometric coherence; global heuristic; image reconstruction; pixel selection; structure-tensor-based data-term; Approximation algorithms; Geometry; Image reconstruction; Signal processing algorithms; Tensile stress; Vectors; Visualization; Examplar-based image inpainting; Patch lookup strategy; Structure tensor analysis;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Image Processing (ICIP), 2014 IEEE International Conference on
Conference_Location :
Paris
Type :
conf
DOI :
10.1109/ICIP.2014.7025937
Filename :
7025937
Link To Document :
بازگشت