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.

@InProceedings\{GS05,
  author       = "Gargallo, Pau and Sturm, Peter",
  title        = "Bayesian 3D Modeling from Images using Multiple Depth Maps",
  booktitle    = "Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, San Diego, California",
  volume       = "2",
  pages        = "885-891",
  month        = "jun",
  year         = "2005",
  url          = "http://perception.inrialpes.fr/Publications/2005/GS05"
}