A Bayesian model for perception of surfaces from binocular disparity

Abstract

We propose a computational model for the perception of surfaces from binocular disparity within a Bayesian framework. The model attempts to reconstruct the perceived surfaces from their differential structure, which is concurrently estimated from initial data of given binocular disparity. To achieve this, the model consists of four processes: a continuous… (More)
DOI: 10.1002/(SICI)1520-684X(199901)30:1%3C32::AID-SCJ4%3E3.0.CO;2-G

Topics

3 Figures and Tables