Convex approach for non-rigid structure from motion via sparse representation

Junjie Hu, Terumasa Aoki

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Citation (Scopus)

Abstract

This paper presents a convex solution for simultaneously recovering 3D non-rigid structures and camera motions from 2D image sequences based on sparse representation. Most existing methods rely on low rank assumption. However, it will lead to poor reconstruction for objects with strong local deformation. Also, when camera motion is unknown, there is no convex solution for non-rigid structure from motion (NRSfM). In order to solve this problem, we estimate non-rigid structures by sparse representation. In this paper, we estimate camera motions through a sparse spectral-norm minimization approach, and then a fast l1-norm minimization algorithm is introduced to reconstruct 3D structures. Both of them are convex, therefore, our method gives a global optimum. Our method can handle objects with strong local deformation and also doesn't need low rank prior. Experimental results show that our method achieves state-of-The-Art reconstruction performance on CMU benchmark dataset.

Original languageEnglish
Title of host publicationVISAPP
EditorsJose Braz, Alain Tremeau, Francisco Imai
PublisherSciTePress
Pages333-339
Number of pages7
ISBN (Electronic)9789897582271
Publication statusPublished - 2017 Jan 1
Event12th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications, VISIGRAPP 2017 - Porto, Portugal
Duration: 2017 Feb 272017 Mar 1

Publication series

NameVISIGRAPP 2017 - Proceedings of the 12th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications
Volume6

Other

Other12th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications, VISIGRAPP 2017
CountryPortugal
CityPorto
Period17/2/2717/3/1

Keywords

  • L1-norm Minimization
  • Non-rigid Structure From Motion
  • Sparse Representation

ASJC Scopus subject areas

  • Computer Graphics and Computer-Aided Design
  • Computer Vision and Pattern Recognition
  • Artificial Intelligence

Fingerprint Dive into the research topics of 'Convex approach for non-rigid structure from motion via sparse representation'. Together they form a unique fingerprint.

Cite this