Accurate light field depth estimation under occlusion

Abstract

Epipolar plane images (EPIs) have advantages in light field depth estimation, but the current EPI-based methods only use one aspect of the information related to the line or its surroundings in EPIs. Moreover, most current methods merely extract the depth map of the target view, ignoring the depth information from other views. To fully utilize the available information, we first introduce a novel data cost by comprehensively utilizing the characteristics of pixel consistency on the line and region difference around the line in EPIs to improve the robustness against occlusion and noise. Then, we put forward a multi-view depth integration strategy that copes with weak texture and occlusion areas. Finally, an edging preserving filter is applied to further refine the depth map. Experiments on synthetic and real light field datasets show that the proposed method outperforms the state-of-the-art light field depth estimation algorithms, especially in the presence of occluded pixels.