Complex non-rigid motion 3D reconstruction by union of subspaces

Zhu, Yingying, Huang, Dong, De LaTorre, Fernando and Lucey, Simon (2014). Complex non-rigid motion 3D reconstruction by union of subspaces. In: Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition CVPR 2014. 27th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2014, Columbus, Ohio, (1542-1549). 23-28 June 2014. doi:10.1109/CVPR.2014.200


Author Zhu, Yingying
Huang, Dong
De LaTorre, Fernando
Lucey, Simon
Title of paper Complex non-rigid motion 3D reconstruction by union of subspaces
Conference name 27th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2014
Conference location Columbus, Ohio
Conference dates 23-28 June 2014
Convener Sven Dickinson
Proceedings title Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition CVPR 2014   Check publisher's open access policy
Journal name IEEE Conference on Computer Vision and Pattern Recognition. Proceedings   Check publisher's open access policy
Series Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
Place of Publication Piscataway NJ United States
Publisher IEEE
Publication Year 2014
Sub-type Fully published paper
DOI 10.1109/CVPR.2014.200
Open Access Status Not yet assessed
ISBN 9781479951178
ISSN 1063-6919
Start page 1542
End page 1549
Total pages 8
Language eng
Abstract/Summary The task of estimating complex non-rigid 3D motion through a monocular camera is of increasing interest to the wider scientific community. Assuming one has the 2D point tracks of the non-rigid object in question, the vision com- munity refers to this problem as Non-Rigid Structure from Motion (NRSfM). In this paper we make two contributions. First, we demonstrate empirically that the current state of the art approach to NRSfM (i.e. Dai et al. [5 ]) exhibits poor reconstruction performance on complex motion (i.e motions involving a sequence of primitive actions such as walk, sit and stand involving a human object). Second, we propose that this limitation can be circumvented by modeling com- plex motion as a union of subspaces. This does not naturally occur in Dai et al.’s approach which instead makes a less compact summation of subspaces assumption. Experiments on both synthetic and real videos illustrate the benefits of our approach for the complex nonrigid motion analysis.
Subjects 1712 Software
1707 Computer Vision and Pattern Recognition
Q-Index Code E1
Q-Index Status Confirmed Code
Institutional Status UQ

Document type: Conference Paper
Sub-type: Fully published paper
Collections: Official 2015 Collection
School of Information Technology and Electrical Engineering Publications
 
Versions
Version Filter Type
Citation counts: TR Web of Science Citation Count  Cited 16 times in Thomson Reuters Web of Science Article | Citations
Scopus Citation Count Cited 29 times in Scopus Article | Citations
Google Scholar Search Google Scholar
Created: Tue, 02 Dec 2014, 14:54:00 EST by System User on behalf of Scholarly Communication and Digitisation Service