• xmlui.mirage2.page-structure.header.title
    • français
    • English
  • Help
  • Login
  • Language 
    • Français
    • English
View Item 
  •   BIRD Home
  • CEREMADE (UMR CNRS 7534)
  • CEREMADE : Publications
  • View Item
  •   BIRD Home
  • CEREMADE (UMR CNRS 7534)
  • CEREMADE : Publications
  • View Item
JavaScript is disabled for your browser. Some features of this site may not work without it.

Browse

BIRDResearch centres & CollectionsBy Issue DateAuthorsTitlesTypeThis CollectionBy Issue DateAuthorsTitlesType

My Account

LoginRegister

Statistics

Most Popular ItemsStatistics by CountryMost Popular Authors
Thumbnail - Request a copy

Using Point Correspondences Without Projective Deformation For Multi-View Stereo Reconstruction

Vincent, Nicole; Cohen, Laurent D.; Auclair, Adrien (2008), Using Point Correspondences Without Projective Deformation For Multi-View Stereo Reconstruction, Conference on Image Processing, 2008. ICIP 2008. 15th IEEE International, IEEE, p. 193-196. http://dx.doi.org/10.1109/ICIP.2008.4711724

Type
Communication / Conférence
Date
2008
Conference title
ICIP 2008
Conference date
2008-09
Conference city
San Diego
Conference country
États-Unis
Book title
Conference on Image Processing, 2008. ICIP 2008. 15th IEEE International
Publisher
IEEE
ISBN
E-ISBN : 978-1-4244-1764-3 Print ISBN: 978-1-4244-1765-0
Pages
193-196
Publication identifier
http://dx.doi.org/10.1109/ICIP.2008.4711724
Metadata
Show full item record
Author(s)
Vincent, Nicole
Cohen, Laurent D.
Auclair, Adrien
Abstract (EN)
This paper proposes a novel algorithm to reconstruct a 3D surface from a calibrated set of images. In a first pass, it uses Scale Invariant Features Transform (SIFT) descriptor correspondences to drive the deformation of a mesh toward the true object surface. We introduce a method to handle the fact that these local descriptors are computed at positions that are not projections of mesh vertices in the images. In order to avoid projective deformations due to the large windows of interest of this descriptor, correspondences are only computed between images from the same viewpoint. This is used in a first pass to recover large concavities of the object. In a second pass, a one dimensional Lucas-Kanade tracker is used to recover small scale details. Using publicly available benchmarks, our algorithm obtains high accuracy while being among the fastest ones.
Subjects / Keywords
Lucas–Kanade method; Pattern recognition systems; Scale Invariant Features Transform

Related items

Showing items related by title and author.

  • Thumbnail
    A Robust Approach for 3D Cars Reconstruction 
    Auclair, Adrien; Cohen, Laurent D.; Vincent, Nicole (2007) Communication / Conférence
  • Thumbnail
    Hash functions for near duplicate image retrieval 
    Auclair, Adrien; Vincent, Nicole; Cohen, Laurent D. (2009) Communication / Conférence
  • Thumbnail
    Hachage de descripteurs locaux pour la recherche d'images similaires 
    Auclair, Adrien; Cohen, Laurent D.; Vincent, Nicole (2009) Communication / Conférence
  • Thumbnail
    How to Use SIFT Vectors to Analyze an Image with Database Templates 
    Auclair, Adrien; Cohen, Laurent D.; Vincent, Nicole (2008) Communication / Conférence
  • Thumbnail
    Deformation Field Estimation for the Cardiac Wall using Doppler Tissue Imaging 
    Moreau, Valérie; Cohen, Laurent D.; Pellerin, D. (2002) Communication / Conférence
Dauphine PSL Bibliothèque logo
Place du Maréchal de Lattre de Tassigny 75775 Paris Cedex 16
Phone: 01 44 05 40 94
Contact
Dauphine PSL logoEQUIS logoCreative Commons logo