Title :
Photo-consistent surface reconstruction from noisy point clouds
Author :
Aganj, Ehsan ; Keriven, Renaud ; Pons, Jean-Philippe
Author_Institution :
CERTIS, Univ. Paris-Est, Marne-la-Vallee, France
Abstract :
Existing algorithms for surface reconstruction from point sets are defeated by moderate amounts of noise and outliers, which makes them unapplicable to point clouds originating from multi-view image data. In this paper, we present a novel method which incorporates the input images in the surface reconstruction process for a better accuracy and robustness. Our approach is based on the medial axis transform of the scene, which our algorithm estimates through a global photo-consistency optimization by simulated annealing. A faithful polyhedral representation of the scene is then obtained by inversion of the medial axis transform.
Keywords :
image reconstruction; image representation; simulated annealing; surface reconstruction; transforms; global photo-consistency optimization; medial axis transform; multiview image data; noise; noisy point clouds; outliers; photo-consistent surface reconstruction; polyhedral representation; simulated annealing; Clouds; Computational geometry; Computational modeling; Image reconstruction; Layout; Noise level; Sampling methods; Shape; Simulated annealing; Surface reconstruction; Surface reconstruction; medial axis transform; point cloud; stereovision;
Conference_Titel :
Image Processing (ICIP), 2009 16th IEEE International Conference on
Conference_Location :
Cairo
Print_ISBN :
978-1-4244-5653-6
Electronic_ISBN :
1522-4880
DOI :
10.1109/ICIP.2009.5413945