Proceedings Article, Paper
@InProceedings
Beitrag in Tagungsband, Workshop


Show entries of:

this year (2019) | last year (2018) | two years ago (2017) | Notes URL

Action:

login to update

Options:








Author, Editor

Author(s):

de Aguiar, Edilson
Theobalt, Christian
Stoll, Carsten
Seidel, Hans-Peter

dblp
dblp
dblp
dblp



Editor(s):

Baker, Simon
Matas, Jiri
Zabih, Ramin

dblp
dblp
dblp

Not MPII Editor(s):

Baker, Simon
Matas, Jiri
Zabih, Ramin

BibTeX cite key*:

deAguiarCVPR2007

Title, Booktitle

Title*:

Marker-less Deformable Mesh Tracking for Human Shape and Motion Capture

Booktitle*:

IEEE International Conference on Computer Vision and Pattern Recognition (CVPR)

Event, URLs

URL of the conference:

http://cvpr.cv.ri.cmu.edu/

URL for downloading the paper:


Event Address*:

Minneapolis, USA

Language:

English

Event Date*
(no longer used):


Organization:

IEEE

Event Start Date:

18 June 2007

Event End Date:

23 June 2007

Publisher

Name*:

IEEE

URL:

http://www.ieee.org/

Address*:

Los Alamitos, USA

Type:


Vol, No, Year, pp.

Series:


Volume:

6

Number:


Month:

June

Pages:

2502-2509

Year*:

2007

VG Wort Pages:

18

ISBN/ISSN:

1-424-41179-3

Sequence Number:


DOI:




Note, Abstract, ©


(LaTeX) Abstract:

We present a novel algorithm to jointly capture the motion and the dynamic shape of humans from
multiple video streams without using optical markers. Instead of relying on kinematic skeletons,
as traditional motion capture methods, our approach uses a deformable high-quality mesh of a human
as scene representation. It jointly uses an image-based
\mbox{3D} correspondence estimation algorithm and a fast
Laplacian mesh deformation scheme to capture both
motion and surface deformation
of the actor from the input video footage. As opposed to many related methods,
our algorithm can track people wearing wide apparel, it can straightforwardly be applied to
any type of subject, e.g. animals, and it preserves the connectivity
of the mesh over time. We demonstrate the performance of our approach using synthetic and
captured real-world video sequences and validate its accuracy by comparison to the ground truth.

Keywords:

Deformable Mesh Tracking, 3D Video, Computer Vision



Download
Access Level:

Public

Correlation

MPG Unit:

Max-Planck-Institut für Informatik



MPG Subunit:

Computer Graphics Group

MPG Subsubunit:

3D Video and Vision-based Graphics

Appearance:

MPII WWW Server, MPII FTP Server, MPG publications list, university publications list, working group publication list, Fachbeirat, VG Wort



BibTeX Entry:

@INPROCEEDINGS{deAguiarCVPR2007,
AUTHOR = {de Aguiar, Edilson and Theobalt, Christian and Stoll, Carsten and Seidel, Hans-Peter},
EDITOR = {Baker, Simon and Matas, Jiri and Zabih, Ramin},
TITLE = {Marker-less Deformable Mesh Tracking for Human Shape and Motion Capture},
BOOKTITLE = {IEEE International Conference on Computer Vision and Pattern Recognition (CVPR)},
PUBLISHER = {IEEE},
YEAR = {2007},
ORGANIZATION = {IEEE},
VOLUME = {6},
PAGES = {2502--2509},
ADDRESS = {Minneapolis, USA},
MONTH = {June},
ISBN = {1-424-41179-3},
}


Entry last modified by Uwe Brahm, 07/01/2009
Show details for Edit History (please click the blue arrow to see the details)Edit History (please click the blue arrow to see the details)
Hide details for Edit History (please click the blue arrow to see the details)Edit History (please click the blue arrow to see the details)

Editor(s)
Christian Theobalt
Created
03/13/2007 04:37:53 PM
Revisions
5.
4.
3.
2.
1.
Editor(s)
Uwe Brahm
Anja Becker
Edilson de Aguiar
Edilson de Aguiar
Edilson de Aguiar
Edit Dates
02/28/2008 04:21:45 PM
22.02.2008 13:11:11
01/05/2008 12:55:17 AM
01/04/2008 09:51:11 PM
03/14/2007 02:13:20 PM
Show details for Attachment SectionAttachment Section
Hide details for Attachment SectionAttachment Section