Thèse de DOCTORAT de l'Institut National Polytechnique
Spécialité: Mathématiques et Informatique
Mr Pau GARGALLO I PIRACES (INP Grenoble)
soutiendra le Lundi 11 Février 2008 à 10h30 Grand Amphi de l'INRIA Rhône-Alpes, Montbonnot
Contributions à l'approche bayésienne pour la stéréovision multi-vues.
Ces travaux se sont déroulés sous la direction de Mr Peter STURM (DR, INRIA Rhône-Alpes)
Multi-view stereo is the problem of recovering the shape of objects
from multiple images taken from different but known camera positions.
It is an inverse problem where we want to find the cause (the object)
given the effect (the images). From a Bayesian perspective, the
solution would be the reconstruction that best reproduces the input
images while at the same time being plausible a priori. Taking this
approach, in this thesis we develop generative models and methods for
computing reconstructions that minimize the difference between the
observed images and the images sythetized from the reconstruction.
Three models are presented. The first, represents the reconstructed
scene by a set of depth maps. This gives high resolution results, but
have problems at the objects boundaries. The second model represents
the scene by a discreet occupancy grid, yielding to a combinatorial
optimization problem, which is addressed through message passing
techniques. The final model represents the scene by a smooth surface
and the resulting optimization problem is solved via gradient descent
In either model, the main difficulty is to correctly take into account
the occlusions that occur during the image formation process.
Modeling self-occlusions results in optimization problems that
challenge current optimization techniques. In this respect, the main
result of the thesis is the computation of the derivative of the
reprojection error with respect to surface variations taking into
account the visibility changes that occur while the surface moves.
This enables the use of gradient descent techniques, and lead to
surface evolutions that places the contour generators of the surface
to their correct location in the images without the need of additional
silhouettes or apparent contours constraints.
Vision par ordinateur, reconstruction 3D, visibilité.