Global priors for binocular stereopsis

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.<<ETX>>

[1]  Anil K. Jain,et al.  Markov Random Field Texture Models , 1983, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[2]  Donald Geman,et al.  Stochastic Relaxation, Gibbs Distributions, and the Bayesian Restoration of Images , 1984, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[3]  J P Frisby,et al.  PMF: A Stereo Correspondence Algorithm Using a Disparity Gradient Limit , 1985, Perception.

[4]  Tomaso Poggio,et al.  Probabilistic Solution of Ill-Posed Problems in Computational Vision , 1987 .

[5]  David B. Cooper,et al.  Toward a Model-Based Bayesian Theory for Estimating and Recognizing Parameterized 3-D Objects Using Two or More Images Taken from Different Positions , 1989, IEEE Trans. Pattern Anal. Mach. Intell..

[6]  James J. Clark,et al.  Data Fusion for Sensory Information Processing Systems , 1990 .

[7]  Federico Girosi,et al.  Parallel and Deterministic Algorithms from MRFs: Surface Reconstruction , 1991, IEEE Trans. Pattern Anal. Mach. Intell..

[8]  Daniel J. Kersten,et al.  The Computation of Stereo Disparity for Transparent and for Opaque Surfaces , 1992, NIPS.

[9]  I. G. MacKenzie,et al.  Stochastic Processes with Applications , 1992 .

[10]  Josiane Zerubia,et al.  Multiscale Markov random field models for parallel image classification , 1993, 1993 (4th) International Conference on Computer Vision.

[11]  Peter N. Belhumeur,et al.  A binocular stereo algorithm for reconstructing sloping, creased, and broken surfaces in the presence of half-occlusion , 1993, 1993 (4th) International Conference on Computer Vision.