International Journal of Computer Vision

, Volume 117, Issue 3, pp 226–246

Complex Non-rigid 3D Shape Recovery Using a Procrustean Normal Distribution Mixture Model

Article

DOI: 10.1007/s11263-015-0860-7

Cite this article as:
Cho, J., Lee, M. & Oh, S. Int J Comput Vis (2016) 117: 226. doi:10.1007/s11263-015-0860-7

Abstract

Recovering the 3D shape of a non-rigid object is a challenging problem. Existing methods make the low-rank assumption and do not scale well with the increased degree of freedom found in complex non-rigid deformations or shape variations. Moreover, in general, the degree of freedom of deformation is assumed to be known in advance, which limits the applicability of non-rigid structure from motion algorithms in a practical situation. In this paper, we propose a method for handling complex shape variations based on the assumption that complex shape variations can be represented probabilistically by a mixture of primitive shape variations. The proposed model is a generative probabilistic model, called a Procrustean normal distribution mixture model, which can model complex shape variations without rank constraints. Experimental results show that the proposed method significantly outperforms existing methods.

Keywords

3D reconstruction Shape analysis Non-rigid structure from motion Non-rigid shape recovery 

Copyright information

© Springer Science+Business Media New York 2015

Authors and Affiliations

  1. 1.Department of Electrical and Computer Engineering and ASRISeoul National UniversitySeoulKorea
  2. 2.Division of Electrical EngineeringHanyang UniversityAnsanKorea

Personalised recommendations