Automatic reconstruction of dense 3D face point cloud with a single depth image

Shu Zhang; Hui Yu; Junyu Dong; Ting Wang; Zhaojie Ju; Honghai Liu

doi:10.1109/SMC.2015.255

Automatic reconstruction of dense 3D face point cloud with a single depth image

Shu Zhang, Hui Yu, Junyu Dong, Ting Wang, Zhaojie Ju, Honghai Liu

School of Computing

Ocean University of China

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

361 Downloads (Pure)

Abstract

Human face analysis is the basis for many other computer vision tasks, such as camera surveillance, entrance authorization and age estimation. With 3D face models, the vision task based on facial analysis can usually achieve a higher accuracy than the 2D cases since it provides more information with the additional dimension. However, most existing 3D face reconstruction methods suffer from complicated processing and high computation. This paper presents a novel method that simplifies the 3D face reconstruction process with only one shot of Kinect data. The output of the system is a high density of 3D face point cloud with smoother surface. This provides rich details of the human face for other computer vision tasks. Experiments with real world data show promising results using the proposed method.

Original language	English
Title of host publication	2015 IEEE International Conference on Systems, Man, and Cybernetics (SMC)
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	1439-1444
DOIs	https://doi.org/10.1109/SMC.2015.255
Publication status	Published - Oct 2015
Event	2015 IEEE International Conference on Systems, Man, and Cybernetics - Hong Kong, China Duration: 9 Oct 2015 → 12 Nov 2015

Conference

Conference	2015 IEEE International Conference on Systems, Man, and Cybernetics
Country/Territory	China
City	Hong Kong
Period	9/10/15 → 12/11/15

Access to Document

10.1109/SMC.2015.255

Automatic_Reconstruction_of_3D_Face
© 2015 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.
Accepted author manuscript (Post-print), 2.77 MB

Cite this

@inproceedings{a0153f775b8d4e94b8d4bb5fdb238838,

title = "Automatic reconstruction of dense 3D face point cloud with a single depth image",

abstract = "Human face analysis is the basis for many other computer vision tasks, such as camera surveillance, entrance authorization and age estimation. With 3D face models, the vision task based on facial analysis can usually achieve a higher accuracy than the 2D cases since it provides more information with the additional dimension. However, most existing 3D face reconstruction methods suffer from complicated processing and high computation. This paper presents a novel method that simplifies the 3D face reconstruction process with only one shot of Kinect data. The output of the system is a high density of 3D face point cloud with smoother surface. This provides rich details of the human face for other computer vision tasks. Experiments with real world data show promising results using the proposed method.",

author = "Shu Zhang and Hui Yu and Junyu Dong and Ting Wang and Zhaojie Ju and Honghai Liu",

year = "2015",

month = oct,

doi = "10.1109/SMC.2015.255",

language = "English",

pages = "1439--1444",

booktitle = "2015 IEEE International Conference on Systems, Man, and Cybernetics (SMC)",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

address = "United States",

note = "2015 IEEE International Conference on Systems, Man, and Cybernetics ; Conference date: 09-10-2015 Through 12-11-2015",

}

Zhang, S, Yu, H, Dong, J, Wang, T, Ju, Z & Liu, H 2015, Automatic reconstruction of dense 3D face point cloud with a single depth image. in 2015 IEEE International Conference on Systems, Man, and Cybernetics (SMC). Institute of Electrical and Electronics Engineers Inc., pp. 1439-1444, 2015 IEEE International Conference on Systems, Man, and Cybernetics, Hong Kong, China, 9/10/15. https://doi.org/10.1109/SMC.2015.255

TY - GEN

T1 - Automatic reconstruction of dense 3D face point cloud with a single depth image

AU - Zhang, Shu

AU - Yu, Hui

AU - Dong, Junyu

AU - Wang, Ting

AU - Ju, Zhaojie

AU - Liu, Honghai

PY - 2015/10

Y1 - 2015/10

N2 - Human face analysis is the basis for many other computer vision tasks, such as camera surveillance, entrance authorization and age estimation. With 3D face models, the vision task based on facial analysis can usually achieve a higher accuracy than the 2D cases since it provides more information with the additional dimension. However, most existing 3D face reconstruction methods suffer from complicated processing and high computation. This paper presents a novel method that simplifies the 3D face reconstruction process with only one shot of Kinect data. The output of the system is a high density of 3D face point cloud with smoother surface. This provides rich details of the human face for other computer vision tasks. Experiments with real world data show promising results using the proposed method.

AB - Human face analysis is the basis for many other computer vision tasks, such as camera surveillance, entrance authorization and age estimation. With 3D face models, the vision task based on facial analysis can usually achieve a higher accuracy than the 2D cases since it provides more information with the additional dimension. However, most existing 3D face reconstruction methods suffer from complicated processing and high computation. This paper presents a novel method that simplifies the 3D face reconstruction process with only one shot of Kinect data. The output of the system is a high density of 3D face point cloud with smoother surface. This provides rich details of the human face for other computer vision tasks. Experiments with real world data show promising results using the proposed method.

U2 - 10.1109/SMC.2015.255

DO - 10.1109/SMC.2015.255

M3 - Conference contribution

SP - 1439

EP - 1444

BT - 2015 IEEE International Conference on Systems, Man, and Cybernetics (SMC)

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2015 IEEE International Conference on Systems, Man, and Cybernetics

Y2 - 9 October 2015 through 12 November 2015

ER -

Automatic reconstruction of dense 3D face point cloud with a single depth image

Abstract

Conference

Access to Document

Fingerprint

Cite this