Skip to Main content Skip to Navigation
New interface
Conference papers

Progressive Surface Reconstruction from Images Using a Local Prior

Gang Zeng Sylvain Paris 1 Long Quan François X. Sillion 2 
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 : This paper introduces a new method for surface reconstruction from multiple calibrated images. The primary contribution of this work is the notion of local prior to combine the flexibility of the carving approach with the accuracy of graph-cut optimization. A progressive refinement scheme is used to recover the topology and reason the visibility of the object. Within each voxel, a detailed surface patch is optimally reconstructed using a graph-cut method. The advantage of this technique is its ability to handle complex shape similarly to level sets while enjoying a higher precision. Compared to carving techniques, the addressed problem is well-posed, and the produced surface does not suffer from aliasing. In addition, our approach seamlessly handles complete and partial reconstructions: If the scene is only partially visible, the process naturally produces an open surface; otherwise, if the scene is fully visible, it creates a complete shape. These properties are demonstrated on real image sequences.
Document type :
Conference papers
Complete list of metadata
Contributor : Team Evasion Connect in order to contact the contributor
Submitted on : Wednesday, October 13, 2010 - 3:18:12 PM
Last modification on : Saturday, November 19, 2022 - 3:58:54 AM
Long-term archiving on: : Friday, January 14, 2011 - 2:29:12 AM


Files produced by the author(s)


  • HAL Id : inria-00510155, version 1


Gang Zeng, Sylvain Paris, Long Quan, François X. Sillion. Progressive Surface Reconstruction from Images Using a Local Prior. International Conference on Computer Vision, 2005, Beijing, China. ⟨inria-00510155⟩



Record views


Files downloads