EPI-Neighborhood Distribution Based Light Field Depth Estimation

Abstract

In this paper, a novel depth estimation algorithm tackling foreground occlusion is proposed based on the neighborhood distribution in the sheared epipolar images (EPIs). First, the EPI is sheared to perform refocusing. Next a series of sheared EPI's neighboring pixels in a local window are selected and the corresponding histogram distributions are analyzed by the proposed novel tensor, Kullback-Leibler Divergence (KLD). Then, depths calculated from vertical and horizontal EPIs' tensors are fused according to the tensors' variation scale for a high quality depth map. Finally, confident depth points are propagated to the whole image by global optimization. Experimental results show that the proposed algorithm achieves better performance relative to state-of-the-art algorithms.