3D geometry from uncalibrated images

  • Authors:
  • George Kamberov;Gerda Kamberova;O. Chum;Š. Obdržálek;D. Martinec;J. Kostková;T. Pajdla;J. Matas;R. Šára

  • Affiliations:
  • Stevens Institute of Technology, Hoboken, NJ;Hofstra University, Hempstead, NY;Center for Machine Perception, Department of Cybernetics, Faculty of Electrical Engineering, Czech Technical University, Prague 6, Czech Republic;Center for Machine Perception, Department of Cybernetics, Faculty of Electrical Engineering, Czech Technical University, Prague 6, Czech Republic;Center for Machine Perception, Department of Cybernetics, Faculty of Electrical Engineering, Czech Technical University, Prague 6, Czech Republic;Center for Machine Perception, Department of Cybernetics, Faculty of Electrical Engineering, Czech Technical University, Prague 6, Czech Republic;Center for Machine Perception, Department of Cybernetics, Faculty of Electrical Engineering, Czech Technical University, Prague 6, Czech Republic;Center for Machine Perception, Department of Cybernetics, Faculty of Electrical Engineering, Czech Technical University, Prague 6, Czech Republic;Center for Machine Perception, Department of Cybernetics, Faculty of Electrical Engineering, Czech Technical University, Prague 6, Czech Republic

  • Venue:
  • ISVC'06 Proceedings of the Second international conference on Advances in Visual Computing - Volume Part II
  • Year:
  • 2006

Quantified Score

Hi-index 0.00

Visualization

Abstract

We present an automatic pipeline for recovering the geometry of a 3D scene from a set of unordered, uncalibrated images. The contributions in the paper are the presentation of the system as a whole, from images to geometry, the estimation of the local scale for various scene components in the orientation-topology module, the procedure for orienting the cloud components, and the method for dealing with points of contact. The methods are aimed to process complex scenes and non-uniformly sampled, noisy data sets.