Propagated Photoconsistency and Convexity in Variational Multiview 3D Reconstruction - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2007

Propagated Photoconsistency and Convexity in Variational Multiview 3D Reconstruction

Kalin Kolev
  • Function : Author
  • PersonId : 847733
Maria Klodt
  • Function : Author
  • PersonId : 847734
Thomas Brox
  • Function : Author
  • PersonId : 847735
Daniel Cremers
  • Function : Author
  • PersonId : 847736

Abstract

In this paper, we make two contributions. Firstly, we replace the generic balloon constraints widely used in 3D reconstruction by a more sophisticated data-dependent regional term. The key idea is to propagate classical photoconsistency along visual rays into regional values describing voxel probabilities for being inside or outside the observed object. Secondly, we cast the optimization as one of minimizing a convex functional. Therefore (up to visibility) the reconstruction problem can be solved in a globally optimal manner in a spatially continuous setting. Compared to graph cut methods, this approach does not suffer from discretization artifacts and exhibits considerable reduction in memory requirements. Experimental comparisons clearly show the advantages of the proposed technique.
Fichier principal
Vignette du fichier
p24.pdf (708.82 Ko) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

inria-00265725 , version 1 (20-03-2008)

Identifiers

  • HAL Id : inria-00265725 , version 1

Cite

Kalin Kolev, Maria Klodt, Thomas Brox, Daniel Cremers. Propagated Photoconsistency and Convexity in Variational Multiview 3D Reconstruction. Proceedings of the First International Workshop on Photometric Analysis For Computer Vision - PACV 2007, Oct 2007, Rio de Janeiro, Brazil. 8 p. ⟨inria-00265725⟩

Collections

PACV2007
215 View
214 Download

Share

Gmail Facebook X LinkedIn More