Complex Non-Rigid Motion 3D Reconstruction by Union of Subspaces - Robotics Institute Carnegie Mellon University

Complex Non-Rigid Motion 3D Reconstruction by Union of Subspaces

Conference Paper, Proceedings of (CVPR) Computer Vision and Pattern Recognition, pp. 1542 - 1549, June, 2014

Abstract

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.

BibTeX

@conference{Zhu-2014-17155,
author = {Yingying Zhu and Dong Huang and Fernando De la Torre Frade and Simon Lucey},
title = {Complex Non-Rigid Motion 3D Reconstruction by Union of Subspaces},
booktitle = {Proceedings of (CVPR) Computer Vision and Pattern Recognition},
year = {2014},
month = {June},
pages = {1542 - 1549},
}