Photo-consistent surface reconstruction from noisy point clouds - École des Ponts ParisTech Access content directly
Conference Papers Year : 2009

Photo-consistent surface reconstruction from noisy point clouds

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.
Fichier principal
Vignette du fichier
ICIP09a.pdf (249.85 Ko) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

hal-00834912 , version 1 (18-06-2013)

Identifiers

  • HAL Id : hal-00834912 , version 1

Cite

Ehsan Aganj, Renaud Keriven, Jean-Philippe Pons. Photo-consistent surface reconstruction from noisy point clouds. ICIP, Nov 2009, Le Caire, Egypt. pp.505-508. ⟨hal-00834912⟩
160 View
229 Download

Share

Gmail Facebook Twitter LinkedIn More