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.
Bayesian 3D modeling from images using multiple depth maps
01.01.2005
1298683 byte
Aufsatz (Konferenz)
Elektronische Ressource
Englisch
Computing depth maps from descent images
British Library Online Contents | 2005
|Extracting View-Dependent Depth Maps from a Collection of Images
British Library Online Contents | 2004
|Registering Depth Maps from Multiple Views Recorded by Color Image Sequences
British Library Online Contents | 1997
|Refinement of depth maps by fusion of multiple estimates
British Library Online Contents | 2013
|