A direct method for modeling non-rigid motion with thin plate spline

Jongwoo Lim, Ming Hsuan Yang

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

58 Citations (Scopus)

Abstract

Thin plate spline (TPS) transformations have been applied to non-rigid shape matching with impressive results. However, existing methods often use a sparse set of point correspondences which are established prior to shape matching. A straightforward approach to finding point correspondences and computing TPS parameters imposes expensive computations, thereby motivating us to develop an efficient solution. In this paper, we present a direct method for recovering non-rigid object motion from its appearance in which the point correspondences are simultaneously established while estimating TPS parameters. The motion parameters are estimated in a stiff-to-flexible approach and the principal appearance deformations are learned that can be utilized for motion analysis and recognition. Numerous experiments demonstrate the efficiency and efficacy of the proposed algorithm in modeling the motion details of non-rigid objects undergoing shape deformation and pose variation.

Original languageEnglish
Title of host publicationProceedings - 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2005
PublisherIEEE Computer Society
Pages1196-1202
Number of pages7
ISBN (Print)0769523722, 9780769523729
DOIs
Publication statusPublished - 2005 Jan 1
Event2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2005 - San Diego, CA, United States
Duration: 2005 Jun 202005 Jun 25

Publication series

NameProceedings - 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2005
VolumeI

Conference

Conference2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2005
CountryUnited States
CitySan Diego, CA
Period05/6/2005/6/25

Fingerprint

Splines
Experiments
Motion analysis

All Science Journal Classification (ASJC) codes

  • Engineering(all)

Cite this

Lim, J., & Yang, M. H. (2005). A direct method for modeling non-rigid motion with thin plate spline. In Proceedings - 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2005 (pp. 1196-1202). [1467402] (Proceedings - 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2005; Vol. I). IEEE Computer Society. https://doi.org/10.1109/CVPR.2005.24
Lim, Jongwoo ; Yang, Ming Hsuan. / A direct method for modeling non-rigid motion with thin plate spline. Proceedings - 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2005. IEEE Computer Society, 2005. pp. 1196-1202 (Proceedings - 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2005).
@inproceedings{35a8b65e0ed54d99a890a91fcd1e8f85,
title = "A direct method for modeling non-rigid motion with thin plate spline",
abstract = "Thin plate spline (TPS) transformations have been applied to non-rigid shape matching with impressive results. However, existing methods often use a sparse set of point correspondences which are established prior to shape matching. A straightforward approach to finding point correspondences and computing TPS parameters imposes expensive computations, thereby motivating us to develop an efficient solution. In this paper, we present a direct method for recovering non-rigid object motion from its appearance in which the point correspondences are simultaneously established while estimating TPS parameters. The motion parameters are estimated in a stiff-to-flexible approach and the principal appearance deformations are learned that can be utilized for motion analysis and recognition. Numerous experiments demonstrate the efficiency and efficacy of the proposed algorithm in modeling the motion details of non-rigid objects undergoing shape deformation and pose variation.",
author = "Jongwoo Lim and Yang, {Ming Hsuan}",
year = "2005",
month = "1",
day = "1",
doi = "10.1109/CVPR.2005.24",
language = "English",
isbn = "0769523722",
series = "Proceedings - 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2005",
publisher = "IEEE Computer Society",
pages = "1196--1202",
booktitle = "Proceedings - 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2005",
address = "United States",

}

Lim, J & Yang, MH 2005, A direct method for modeling non-rigid motion with thin plate spline. in Proceedings - 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2005., 1467402, Proceedings - 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2005, vol. I, IEEE Computer Society, pp. 1196-1202, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2005, San Diego, CA, United States, 05/6/20. https://doi.org/10.1109/CVPR.2005.24

A direct method for modeling non-rigid motion with thin plate spline. / Lim, Jongwoo; Yang, Ming Hsuan.

Proceedings - 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2005. IEEE Computer Society, 2005. p. 1196-1202 1467402 (Proceedings - 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2005; Vol. I).

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

TY - GEN

T1 - A direct method for modeling non-rigid motion with thin plate spline

AU - Lim, Jongwoo

AU - Yang, Ming Hsuan

PY - 2005/1/1

Y1 - 2005/1/1

N2 - Thin plate spline (TPS) transformations have been applied to non-rigid shape matching with impressive results. However, existing methods often use a sparse set of point correspondences which are established prior to shape matching. A straightforward approach to finding point correspondences and computing TPS parameters imposes expensive computations, thereby motivating us to develop an efficient solution. In this paper, we present a direct method for recovering non-rigid object motion from its appearance in which the point correspondences are simultaneously established while estimating TPS parameters. The motion parameters are estimated in a stiff-to-flexible approach and the principal appearance deformations are learned that can be utilized for motion analysis and recognition. Numerous experiments demonstrate the efficiency and efficacy of the proposed algorithm in modeling the motion details of non-rigid objects undergoing shape deformation and pose variation.

AB - Thin plate spline (TPS) transformations have been applied to non-rigid shape matching with impressive results. However, existing methods often use a sparse set of point correspondences which are established prior to shape matching. A straightforward approach to finding point correspondences and computing TPS parameters imposes expensive computations, thereby motivating us to develop an efficient solution. In this paper, we present a direct method for recovering non-rigid object motion from its appearance in which the point correspondences are simultaneously established while estimating TPS parameters. The motion parameters are estimated in a stiff-to-flexible approach and the principal appearance deformations are learned that can be utilized for motion analysis and recognition. Numerous experiments demonstrate the efficiency and efficacy of the proposed algorithm in modeling the motion details of non-rigid objects undergoing shape deformation and pose variation.

UR - http://www.scopus.com/inward/record.url?scp=33745133413&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=33745133413&partnerID=8YFLogxK

U2 - 10.1109/CVPR.2005.24

DO - 10.1109/CVPR.2005.24

M3 - Conference contribution

AN - SCOPUS:33745133413

SN - 0769523722

SN - 9780769523729

T3 - Proceedings - 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2005

SP - 1196

EP - 1202

BT - Proceedings - 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2005

PB - IEEE Computer Society

ER -

Lim J, Yang MH. A direct method for modeling non-rigid motion with thin plate spline. In Proceedings - 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2005. IEEE Computer Society. 2005. p. 1196-1202. 1467402. (Proceedings - 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2005). https://doi.org/10.1109/CVPR.2005.24