Hand-held acquisition of 3D models with a video camera

  • Authors:
  • M. Pollefeys;R. Koch;M. Vergauwen;L. Van Gool

  • Affiliations:
  • ESAT-PSI, K.U. Leuven, Heverlee, Belgium;lnst. for Computer Science, Universität Kiel, Germany and ESAT-PSI, K.U. Leuven, Heverlee, Belgium;ESAT-PSI, K.U. Leuven, Heverlee, Belgium;ESAT-PSI, K.U. Leuven, Heverlee, Belgium

  • Venue:
  • 3DIM'99 Proceedings of the 2nd international conference on 3-D digital imaging and modeling
  • Year:
  • 1999

Quantified Score

Hi-index 0.00

Visualization

Abstract

Modeling of 3D objects from image sequences is a challenging problem and has been a research topic for many years. Important theoretical and algorithmic results were achieved that allow to extract even complex 3D scene models from images. One recent effort has been to reduce the amount of calibration and to avoid restrictions on the camera motion. In this contribution an approach is described which achieves this goal by combining state-of-the-art algorithms for uncalibrated projective reconstruction, self-calibration and dense correspondence matching.