Multi-body non-rigid structure-from-motion

Suryansh Kumar, Yuchao Dai, Hongdong Li

科研成果: 书/报告/会议事项章节会议稿件同行评审

31 引用 (Scopus)

摘要

In this paper, we present the first multi-body non-rigid structure-from-motion (SFM) method, which simultaneously reconstructs and segments multiple objects that are undergoing non-rigid deformation over time. Under our formulation, 3D trajectories for each non-rigid object can be well approximated with a sparse affine combination of other 3D trajectories from the same object. The resultant optimization is solved by the alternating direction method of multipliers (ADMM). We demonstrate the efficacy of the proposed method through extensive experiments on both synthetic and real data sequences. Our method outperforms other alternative methods, such as first clustering the 2D feature tracks to groups and then doing non-rigid reconstruction in each group or first conducting 3D reconstruction by using single subspace assumption and then clustering the 3D trajectories into groups.

源语言英语
主期刊名Proceedings - 2016 4th International Conference on 3D Vision, 3DV 2016
出版商Institute of Electrical and Electronics Engineers Inc.
148-156
页数9
ISBN(电子版)9781509054077
DOI
出版状态已出版 - 15 12月 2016
已对外发布
活动4th International Conference on 3D Vision, 3DV 2016 - Stanford, 美国
期限: 25 10月 201628 10月 2016

出版系列

姓名Proceedings - 2016 4th International Conference on 3D Vision, 3DV 2016

会议

会议4th International Conference on 3D Vision, 3DV 2016
国家/地区美国
Stanford
时期25/10/1628/10/16

指纹

探究 'Multi-body non-rigid structure-from-motion' 的科研主题。它们共同构成独一无二的指纹。

引用此