期刊
IEEE JOURNAL OF SELECTED TOPICS IN SIGNAL PROCESSING
卷 11, 期 7, 页码 965-978出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/JSTSP.2017.2730818
关键词
Anti-occlusion depth estimation; light field; occlusion model
资金
- National Natural Science Foundation of China [61531014, 61401359, 61272287]
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 occlusionmodel 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.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据