One-View Occlusion Detection for Stereo Matching With a Fully Connected CRF Model

Abstract

In this paper, we extend the standard belief propagation (BP) sequential technique proposed in the tree-reweighted sequential method [15] to the fully connected CRF models with the geodesic distance affinity. The proposed method has been applied to the stereo matching problem. Also a new approach to the BP marginal solution is proposed that we call one-view occlusion detection (OVOD). In contrast to the standard winner takes all (WTA) estimation, the proposed OVOD solution allows to find occluded regions in the disparity map and simultaneously improve the matching result. As a result we can perform only one energy minimization process and avoid the cost calculation for the second view and the left-right check procedure. We show that the OVOD approach considerably improves results for cost augmentation and energy minimization techniques in comparison with the standard one-view affinity space implementation. We apply our method to the Middlebury data set and reach state-ofthe-art especially for median, average and mean squared error metrics.

mproved Stereo Matching Algorithm based on Census Transform and Dynamic Histogram Cost Computation

“…[12] proposed a different and new taxonomy called PatchMatch-based using superpixel cut and utilized the 3D labels of an image as matching cost computation accurately. More advanced algorithms utilized CNN-based matching cost function as segment of binary abilities in the energy function's smoothness term employed by [13].…”

Asymmetric Learning for Stereo Matching Cost Computation

“…Therefore, the core task of the stereo method is to find the one-to-one correspondence between pixels. Methods that solve the stereo matching problem can be divided into two categories: cost filtering methods and energy minimization methods [1]. Scharstein and Szeliski [2] summarized the steps of the stereo matching algorithms as follows: matching cost computation, cost aggregation, disparity computation/optimization, and disparity refinement.…”