4D Light field superpixel and segmentation

Hao Zhu, Qi Zhang, Qing Wang

科研成果: 书/报告/会议事项章节会议稿件同行评审

32 引用 (Scopus)

摘要

Superpixel segmentation of 2D image has been widely used in many computer vision tasks. However, limited to the Gaussian imaging principle, there is not a thorough segmentation solution to the ambiguity in defocus and occlusion boundary areas. In this paper, we consider the essential element of image pixel, i.e., rays in the light space, and propose light field superpixel (LFSP) segmentation to eliminate the ambiguity. The LFSP is first defined mathematically and then a refocus-invariant metric named LFSP self-similarity is proposed to evaluate the segmentation performance. By building a clique system containing 80 neighbors in light field, a robust refocus-invariant LFSP segmentation algorithm is developed. Experimental results on both synthetic and real light field datasets demonstrate the advantages over the state-of-the-arts in terms of traditional evaluation metrics. Additionally the LFSP self-similarity evaluation under different light field refocus levels shows the refocus-invariance of the proposed algorithm.

源语言英语
主期刊名Proceedings - 30th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017
出版商Institute of Electrical and Electronics Engineers Inc.
6709-6717
页数9
ISBN(电子版)9781538604571
DOI
出版状态已出版 - 6 11月 2017
活动30th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017 - Honolulu, 美国
期限: 21 7月 201726 7月 2017

出版系列

姓名Proceedings - 30th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017
2017-January

会议

会议30th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017
国家/地区美国
Honolulu
时期21/07/1726/07/17

指纹

探究 '4D Light field superpixel and segmentation' 的科研主题。它们共同构成独一无二的指纹。

引用此