Adaptive multi-resolution fitting and its application to realistic head modeling

Chenghua Xu; Long Quan; Yunhong Wang; Tieniu Tan; Maxime Lhuillier

doi:10.1016/j.jep.2004.01.012

Adaptive multi-resolution fitting and its application to realistic head modeling

Chenghua Xu^*
, Long Quan
, Yunhong Wang
, Tieniu Tan
, Maxime Lhuillier

^*Corresponding author for this work

CAS - Institute of Automation
Hong Kong University of Science and Technology

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

8 Scopus citations

Abstract

The general approach for object modeling is to construct the surface from the high-quality range points obtained from laser scanners. In this paper, we face the noise point cloud obtained from image sequences by a common camera and develop a novel algorithm of Adaptive Multi-Resolution Fitting (AMRF) for object modeling. This algorithm combines the adaptive subdivision scheme with multi-resolution fitting so that the control model is subdivided locally and adaptively according to the local complexity of the point cloud and approximates the 3D data level by level. The proposed method can conquer the holes and outliers efficiently and create full compatibility between the complexity of the mesh model and the representation of the local details. We apply the proposed method to the complete head modeling with the real data, and the results seem very promising.

Original language	English
Title of host publication	Proceedings - Geometric Modeling and Processing 2004
Publisher	IEEE Computer Society
Pages	345-348
Number of pages	4
ISBN (Print)	0769520782, 9780769520780
DOIs	https://doi.org/10.1016/j.jep.2004.01.012
State	Published - 2004
Externally published	Yes
Event	Proceedings - Geometric Modeling and Processing 2004 - Beijing, China Duration: 13 Apr 2004 → 15 Apr 2004

Publication series

Name	Proceedings - Geometric Modeling and Processing 2004

Conference

Conference	Proceedings - Geometric Modeling and Processing 2004
Country/Territory	China
City	Beijing
Period	13/04/04 → 15/04/04

Keywords

3D head modeling
Adaptive subdivision
Multi-resolution fitting
Optimization

Access to Document

10.1016/j.jep.2004.01.012

Cite this

@inproceedings{a686b4f1f1f04bfca8dbc8af3b5f395a,

title = "Adaptive multi-resolution fitting and its application to realistic head modeling",

abstract = "The general approach for object modeling is to construct the surface from the high-quality range points obtained from laser scanners. In this paper, we face the noise point cloud obtained from image sequences by a common camera and develop a novel algorithm of Adaptive Multi-Resolution Fitting (AMRF) for object modeling. This algorithm combines the adaptive subdivision scheme with multi-resolution fitting so that the control model is subdivided locally and adaptively according to the local complexity of the point cloud and approximates the 3D data level by level. The proposed method can conquer the holes and outliers efficiently and create full compatibility between the complexity of the mesh model and the representation of the local details. We apply the proposed method to the complete head modeling with the real data, and the results seem very promising.",

keywords = "3D head modeling, Adaptive subdivision, Multi-resolution fitting, Optimization",

author = "Chenghua Xu and Long Quan and Yunhong Wang and Tieniu Tan and Maxime Lhuillier",

year = "2004",

doi = "10.1016/j.jep.2004.01.012",

language = "英语",

isbn = "0769520782",

series = "Proceedings - Geometric Modeling and Processing 2004",

publisher = "IEEE Computer Society",

pages = "345--348",

booktitle = "Proceedings - Geometric Modeling and Processing 2004",

address = "美国",

note = "Proceedings - Geometric Modeling and Processing 2004 ; Conference date: 13-04-2004 Through 15-04-2004",

}

Xu, C, Quan, L, Wang, Y, Tan, T & Lhuillier, M 2004, Adaptive multi-resolution fitting and its application to realistic head modeling. in Proceedings - Geometric Modeling and Processing 2004. Proceedings - Geometric Modeling and Processing 2004, IEEE Computer Society, pp. 345-348, Proceedings - Geometric Modeling and Processing 2004, Beijing, China, 13/04/04. https://doi.org/10.1016/j.jep.2004.01.012

Adaptive multi-resolution fitting and its application to realistic head modeling. / Xu, Chenghua; Quan, Long; Wang, Yunhong et al.
Proceedings - Geometric Modeling and Processing 2004. IEEE Computer Society, 2004. p. 345-348 (Proceedings - Geometric Modeling and Processing 2004).

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

TY - GEN

T1 - Adaptive multi-resolution fitting and its application to realistic head modeling

AU - Xu, Chenghua

AU - Quan, Long

AU - Wang, Yunhong

AU - Tan, Tieniu

AU - Lhuillier, Maxime

PY - 2004

Y1 - 2004

N2 - The general approach for object modeling is to construct the surface from the high-quality range points obtained from laser scanners. In this paper, we face the noise point cloud obtained from image sequences by a common camera and develop a novel algorithm of Adaptive Multi-Resolution Fitting (AMRF) for object modeling. This algorithm combines the adaptive subdivision scheme with multi-resolution fitting so that the control model is subdivided locally and adaptively according to the local complexity of the point cloud and approximates the 3D data level by level. The proposed method can conquer the holes and outliers efficiently and create full compatibility between the complexity of the mesh model and the representation of the local details. We apply the proposed method to the complete head modeling with the real data, and the results seem very promising.

AB - The general approach for object modeling is to construct the surface from the high-quality range points obtained from laser scanners. In this paper, we face the noise point cloud obtained from image sequences by a common camera and develop a novel algorithm of Adaptive Multi-Resolution Fitting (AMRF) for object modeling. This algorithm combines the adaptive subdivision scheme with multi-resolution fitting so that the control model is subdivided locally and adaptively according to the local complexity of the point cloud and approximates the 3D data level by level. The proposed method can conquer the holes and outliers efficiently and create full compatibility between the complexity of the mesh model and the representation of the local details. We apply the proposed method to the complete head modeling with the real data, and the results seem very promising.

KW - 3D head modeling

KW - Adaptive subdivision

KW - Multi-resolution fitting

KW - Optimization

UR - https://www.scopus.com/pages/publications/4544220039

U2 - 10.1016/j.jep.2004.01.012

DO - 10.1016/j.jep.2004.01.012

M3 - 会议稿件

AN - SCOPUS:4544220039

SN - 0769520782

SN - 9780769520780

T3 - Proceedings - Geometric Modeling and Processing 2004

SP - 345

EP - 348

BT - Proceedings - Geometric Modeling and Processing 2004

PB - IEEE Computer Society

T2 - Proceedings - Geometric Modeling and Processing 2004

Y2 - 13 April 2004 through 15 April 2004

ER -

Adaptive multi-resolution fitting and its application to realistic head modeling

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this