Quality dynamic human body modeling using a single low-cost depth camera

Qing Zhang; Bo Fu; Mao Ye; Ruigang Yang

doi:10.1109/CVPR.2014.92

Quality dynamic human body modeling using a single low-cost depth camera

Qing Zhang, Bo Fu, Mao Ye, Ruigang Yang

Computer Science

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

77 Scopus citations

Abstract

In this paper we present a novel autonomous pipeline to build a personalized parametric model (pose-driven avatar) using a single depth sensor. Our method first captures a few high-quality scans of the user rotating herself at multiple poses from different views. We fit each incomplete scan using template fitting techniques with a generic human template, and register all scans to every pose using global consistency constraints. After registration, these watertight models with different poses are used to train a parametric model in a fashion similar to the SCAPE method. Once the parametric model is built, it can be used as an animitable avatar or more interestingly synthesizing dynamic 3D models from single-view depth videos. Experimental results demonstrate the effectiveness of our system to produce dynamic models.

Original language	English
Title of host publication	Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
Pages	676-683
Number of pages	8
ISBN (Electronic)	9781479951178, 9781479951178
DOIs	https://doi.org/10.1109/CVPR.2014.92
State	Published - Sep 24 2014
Event	27th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2014 - Columbus, United States Duration: Jun 23 2014 → Jun 28 2014

Publication series

Name	Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
ISSN (Print)	1063-6919

Conference

Conference	27th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2014
Country/Territory	United States
City	Columbus
Period	6/23/14 → 6/28/14

Bibliographical note

Publisher Copyright:
© 2014 IEEE.

Keywords

3D Model
Avatar
Mesh Registration
SCAPE
Template Fitting

ASJC Scopus subject areas

Software
Computer Vision and Pattern Recognition

Access to Document

10.1109/CVPR.2014.92

Cite this

Zhang, Q., Fu, B., Ye, M., & Yang, R. (2014). Quality dynamic human body modeling using a single low-cost depth camera. In Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition (pp. 676-683). Article 6909487 (Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition). https://doi.org/10.1109/CVPR.2014.92

@inproceedings{d6bc12c180de438985d4e1a3b89d225d,

title = "Quality dynamic human body modeling using a single low-cost depth camera",

abstract = "In this paper we present a novel autonomous pipeline to build a personalized parametric model (pose-driven avatar) using a single depth sensor. Our method first captures a few high-quality scans of the user rotating herself at multiple poses from different views. We fit each incomplete scan using template fitting techniques with a generic human template, and register all scans to every pose using global consistency constraints. After registration, these watertight models with different poses are used to train a parametric model in a fashion similar to the SCAPE method. Once the parametric model is built, it can be used as an animitable avatar or more interestingly synthesizing dynamic 3D models from single-view depth videos. Experimental results demonstrate the effectiveness of our system to produce dynamic models.",

keywords = "3D Model, Avatar, Mesh Registration, SCAPE, Template Fitting",

author = "Qing Zhang and Bo Fu and Mao Ye and Ruigang Yang",

note = "Publisher Copyright: {\textcopyright} 2014 IEEE.; 27th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2014 ; Conference date: 23-06-2014 Through 28-06-2014",

year = "2014",

month = sep,

day = "24",

doi = "10.1109/CVPR.2014.92",

language = "English",

series = "Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition",

pages = "676--683",

booktitle = "Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition",

}

Zhang, Q, Fu, B, Ye, M & Yang, R 2014, Quality dynamic human body modeling using a single low-cost depth camera. in Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition., 6909487, Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp. 676-683, 27th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2014, Columbus, United States, 6/23/14. https://doi.org/10.1109/CVPR.2014.92

Quality dynamic human body modeling using a single low-cost depth camera. / Zhang, Qing; Fu, Bo; Ye, Mao et al.
Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition. 2014. p. 676-683 6909487 (Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Quality dynamic human body modeling using a single low-cost depth camera

AU - Zhang, Qing

AU - Fu, Bo

AU - Ye, Mao

AU - Yang, Ruigang

PY - 2014/9/24

Y1 - 2014/9/24

N2 - In this paper we present a novel autonomous pipeline to build a personalized parametric model (pose-driven avatar) using a single depth sensor. Our method first captures a few high-quality scans of the user rotating herself at multiple poses from different views. We fit each incomplete scan using template fitting techniques with a generic human template, and register all scans to every pose using global consistency constraints. After registration, these watertight models with different poses are used to train a parametric model in a fashion similar to the SCAPE method. Once the parametric model is built, it can be used as an animitable avatar or more interestingly synthesizing dynamic 3D models from single-view depth videos. Experimental results demonstrate the effectiveness of our system to produce dynamic models.

AB - In this paper we present a novel autonomous pipeline to build a personalized parametric model (pose-driven avatar) using a single depth sensor. Our method first captures a few high-quality scans of the user rotating herself at multiple poses from different views. We fit each incomplete scan using template fitting techniques with a generic human template, and register all scans to every pose using global consistency constraints. After registration, these watertight models with different poses are used to train a parametric model in a fashion similar to the SCAPE method. Once the parametric model is built, it can be used as an animitable avatar or more interestingly synthesizing dynamic 3D models from single-view depth videos. Experimental results demonstrate the effectiveness of our system to produce dynamic models.

KW - 3D Model

KW - Avatar

KW - Mesh Registration

KW - SCAPE

KW - Template Fitting

UR - http://www.scopus.com/inward/record.url?scp=84911442928&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84911442928&partnerID=8YFLogxK

U2 - 10.1109/CVPR.2014.92

DO - 10.1109/CVPR.2014.92

M3 - Conference contribution

AN - SCOPUS:84911442928

T3 - Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition

SP - 676

EP - 683

BT - Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition

T2 - 27th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2014

Y2 - 23 June 2014 through 28 June 2014

ER -

Quality dynamic human body modeling using a single low-cost depth camera

Abstract

Publication series

Conference

Bibliographical note

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this