Skip to Main content Skip to Navigation
Conference papers

Surface Reconstruction by Propagating 3D Stereo Data in Multiple 2D Images

Gang Zeng 1 Sylvain Paris 2 Long Quan 1 Maxime Lhuillier 3 
2 ARTIS - Acquisition, representation and transformations for image synthesis
GRAVIR - IMAG - Laboratoire d'informatique GRAphique, VIsion et Robotique de Grenoble, Inria Grenoble - Rhône-Alpes, CNRS - Centre National de la Recherche Scientifique : FR71
Abstract : We present a noval approach to surface reconstruction from multiple images. The central idea is to explore the integration of both 3D stereo data and 2D calibrated images. This is motivated by the fact that only robust and accurate feature points that survived the geometry scrutiny of multiple images are reconstructed in space. The density insufficiency and the inevitable holes in the stereo data should be filled in by using information from multiple images. The idea is therefore to first construct small surface patches from stereo points, then to progressively propagate only reliable patches in their neighborhood from images into the whole surface using a best-first strategy. The problem reduces to searching for an optimal local surface patch going through a given set of stereo points from images. This constrained optimization for a surface patch could be handled by a local graph-cut that we develop. Real experiments demonstrate the usability and accuracy of the approach.
Document type :
Conference papers
Complete list of metadata

Cited literature [28 references]  Display  Hide  Download
Contributor : Maxime Lhuillier Connect in order to contact the contributor
Submitted on : Tuesday, December 5, 2006 - 4:52:21 PM
Last modification on : Friday, February 4, 2022 - 3:08:53 AM
Long-term archiving on: : Tuesday, April 6, 2010 - 8:29:22 PM


Files produced by the author(s)


  • HAL Id : hal-00118590, version 1



Gang Zeng, Sylvain Paris, Long Quan, Maxime Lhuillier. Surface Reconstruction by Propagating 3D Stereo Data in Multiple 2D Images. The 8th European Conference on Computer Vision, 2004, France. p. 163-174. ⟨hal-00118590⟩



Record views


Files downloads