Occlusion-Model Guided Antiocclusion Depth Estimation in Light Field

Occlusion is one of the most challenging problems in depth estimation. Previous work has modeled the single-occluder occlusion in light field and achieves good performances, however it is still difficult to obtain accurate depth for multioccluder occlusion. In this paper, we explore the complete occlusion model in light field and derive the occluder-consistency between the spatial and angular spaces, which is used as a guidance to select unoccluded views for each candidate occlusion point. Then, an antiocclusion energy function is built to regularize the depth map. Experimental results on both synthetic and real light-field datasets have demonstrated the advantages of the proposed algorithm compared with state-of-the-art algorithms of light-field depth estimation, especially in multioccluder cases.