Sciweavers

Share
CVPR
2005
IEEE

Bayesian 3D Modeling from Images Using Multiple Depth Maps

10 years 10 months ago
Bayesian 3D Modeling from Images Using Multiple Depth Maps
This paper addresses the problem of reconstructing the geometry and color of a Lambertian scene, given some fully calibrated images acquired with wide baselines. In order to completely model the input data, we propose to represent the scene as a set of colored depth maps, one per input image. We formulate the problem as a Bayesian MAP problem which leads to an energy minimization method. Hidden visibility variables are used to deal with occlusion, reflections and outliers. The main contributions of this work are: a prior for the visibility variables that treats the geometric occlusions; and a prior for the multiple depth maps model that smoothes and merges the depth maps while enabling discontinuities. Real world examples showing the efficiency and limitations of the approach are presented.
Pau Gargallo, Peter F. Sturm
Added 12 Oct 2009
Updated 29 Oct 2009
Type Conference
Year 2005
Where CVPR
Authors Pau Gargallo, Peter F. Sturm
Comments (0)
books