A Switched Gaussian Process for Estimating Disparity and Segmentation in Binocular Stereo

Abstract

This paper describes a Gaussian process framework for inferring pixel-wise disparity and bi-layer segmentation of a scene given a stereo pair of images. The Gaussian process covariance is parameterized by a foreground-backgroundocclusion segmentation label to model both smooth regions and discontinuities. As such, we call our model a switched Gaussian process. We propose a greedy incremental algorithm for adding observations from the data and assigning segmentation labels. Two observation schedules are proposed: the first treats scanlines as independent, the second uses an active learning criterion to select a sparse subset of points to measure. We show that this probabilistic framework has comparable performance to the state-of-the-art.