Develops a Bayesian feedback method for incorporating global structure into prior models for binocular stereopsis. Since most stereo scenes contain either background continuation (large background surfaces continuing behind smaller fore-ground surfaces) or transparency continuation (small opaque patches on a transparent surface), highly nonlocal interactions are often present in the scene geometry. The commonly used local prior models which impose piecewise smoothness constraints on the reconstructions do not capture the probabilistic subtleties of global 3D structures. Therefore, the authors develop a hybridized prior which balances the local properties of the scene geometry with the global properties. Experimental results demonstrating the potential of this technique are provided.<>
Global priors for binocular stereopsis
Proceedings of 1st International Conference on Image Processing ; 2 ; 730-734 vol.2
1994-01-01
487661 byte
Conference paper
Electronic Resource
English
Global Priors for Binocular Stereopsis
British Library Conference Proceedings | 1994
|Binocular Helmholtz stereopsis
IEEE | 2003
|Binocular Helmholtz Stereopsis
British Library Conference Proceedings | 2003
|A Bayesian Approach to Binocular Stereopsis
British Library Online Contents | 1996
|Image‐Aided Navigation Using Cooperative Binocular Stereopsis
Online Contents | 2015
|