International Journal of Computer Vision

, Volume 52, Issue 1, pp 45–64

Constrained Structure and Motion From Multiple Uncalibrated Views of a Piecewise Planar Scene

  • Adrien Bartoli
  • Peter Sturm

DOI: 10.1023/A:1022318524906

Cite this article as:
Bartoli, A. & Sturm, P. International Journal of Computer Vision (2003) 52: 45. doi:10.1023/A:1022318524906


This paper is about multi-view modeling of a rigid scene. We merge the traditional approaches of reconstructing image-extractable features and of modeling via user-provided geometry. We use features to obtain a first guess for structure and motion, fit geometric primitives, correct the structure so that reconstructed features lie exactly on geometric primitives and optimize both structure and motion in a bundle adjustment manner while enforcing the underlying constraints. We specialize this general scheme to the point features and the plane geometric primitives. The underlying geometric relationships are described by multi-coplanarity constraints. We propose a minimal parameterization of the structure enforcing these constraints and use it to devise the corresponding maximum likelihood estimator. The recovered primitives are then textured from the input images. The result is an accurate and photorealistic model.

Experimental results using simulated data confirm that the accuracy of the model using the constrained methods is of clearly superior quality compared to that of traditional methods and that our approach performs better than existing ones, for various scene configurations. In addition, we observe that the method still performs better in a number of configurations when the observed surfaces are not exactly planar. We also validate our method using real images.

3D reconstructionpiecewise planar sceneconstrained structure and motionmaximum likelihood estimator

Copyright information

© Kluwer Academic Publishers 2003

Authors and Affiliations

  • Adrien Bartoli
    • 1
  • Peter Sturm
    • 1
  1. 1.INRIA Rhône-AlpesSaint Ismier cedexFrance