Hierarchical stochastic diffusion for disparity estimation

Abstract

This paper proposes a stochastic approach to estimate the disparity field combined with line field. In the maximum a posteriori (MAP) method based on Markov random field (MRF) model, it is important to optimize and converge the Gibbs potential function corresponding to the perturbed disparity field. The proposed optimization method, stochastic diffusion, takes advantage of the probabilistic distribution of the neighborhood fields, and diffuses the Gibbs potential space to be stable iteratively. By using the neighborhood distribution in the non-random and non-deterministic diffusion, the stochastic diffusion improves both the estimation accuracy and the convergence speed. In the paper, the hierarchical stochastic diffusion is also applied to the disparity field. The hierarchical approach reduces the memory and computational load, and increases the convergence of the potential space. The line field is the discontinuity model of the disparity field. The paper also proposes an effective configuration of the neighborhood to be suitable for the hierarchical disparity structure. According to the experiments, the stochastic diffusion shows good estimation performance. The line field improves the estimation at the object boundary, and the estimated line field coincides with the object boundary with the useful contours. Furthermore, the stochastic diffusion with line field embeds the occlusion detection and compensation. And, the stochastic diffusion converges the estimated fields very fast in the hierarchical scheme. The stochastic diffusion is applicable to any kind of field estimation given the appropriate definition of the field and MRF models.