Morphable face reconstruction with multiple views

Xiaowen Wang; Wei Liang; Liuxin Zhang

doi:10.1109/IHMSC.2010.163

Morphable face reconstruction with multiple views

Xiaowen Wang^*, Wei Liang, Liuxin Zhang

^*Corresponding author for this work

School of Computer Science and Technology

Beijing Institute of Technology

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

6 Citations (Scopus)

Abstract

The morphable modeling method of reconstructing 3D human face is based on a single given image, and the model fitting is ambiguous owing to the lack of depth information and geometry constraints between images. In this paper, we introduce a new face reconstruction method from multiple views based on the morphable model. The morphable face model is matched with multiple face images from different views. Using the multi-view geometry constraints, the ambiguity is efficiently eliminated and more realistic results are provided. We test our algorithm on the MPI face database and real images from our multi-camera system. The experimental results show the efficiency of the proposed method.

Original language	English
Title of host publication	Proceedings - 2010 2nd International Conference on Intelligent Human-Machine Systems and Cybernetics, IHMSC 2010
Pages	250-253
Number of pages	4
DOIs	https://doi.org/10.1109/IHMSC.2010.163
Publication status	Published - 2010
Event	2010 2nd International Conference on Intelligent Human-Machine Systems and Cybernetics, IHMSC 2010 - Nanjing, China Duration: 26 Aug 2010 → 28 Aug 2010

Publication series

Name	Proceedings - 2010 2nd International Conference on Intelligent Human-Machine Systems and Cybernetics, IHMSC 2010
Volume	2

Conference

Conference	2010 2nd International Conference on Intelligent Human-Machine Systems and Cybernetics, IHMSC 2010
Country/Territory	China
City	Nanjing
Period	26/08/10 → 28/08/10

Keywords

3D human face reconstruction
Morphable model
Multiple cameras

Access to Document

10.1109/IHMSC.2010.163

Cite this

Wang, X., Liang, W., & Zhang, L. (2010). Morphable face reconstruction with multiple views. In Proceedings - 2010 2nd International Conference on Intelligent Human-Machine Systems and Cybernetics, IHMSC 2010 (pp. 250-253). Article 5590895 (Proceedings - 2010 2nd International Conference on Intelligent Human-Machine Systems and Cybernetics, IHMSC 2010; Vol. 2). https://doi.org/10.1109/IHMSC.2010.163

@inproceedings{1921cfe1ac6b4e65b0966dfd63ea9493,

title = "Morphable face reconstruction with multiple views",

abstract = "The morphable modeling method of reconstructing 3D human face is based on a single given image, and the model fitting is ambiguous owing to the lack of depth information and geometry constraints between images. In this paper, we introduce a new face reconstruction method from multiple views based on the morphable model. The morphable face model is matched with multiple face images from different views. Using the multi-view geometry constraints, the ambiguity is efficiently eliminated and more realistic results are provided. We test our algorithm on the MPI face database and real images from our multi-camera system. The experimental results show the efficiency of the proposed method.",

keywords = "3D human face reconstruction, Morphable model, Multiple cameras",

author = "Xiaowen Wang and Wei Liang and Liuxin Zhang",

year = "2010",

doi = "10.1109/IHMSC.2010.163",

language = "English",

isbn = "9780769541518",

series = "Proceedings - 2010 2nd International Conference on Intelligent Human-Machine Systems and Cybernetics, IHMSC 2010",

pages = "250--253",

booktitle = "Proceedings - 2010 2nd International Conference on Intelligent Human-Machine Systems and Cybernetics, IHMSC 2010",

note = "2010 2nd International Conference on Intelligent Human-Machine Systems and Cybernetics, IHMSC 2010 ; Conference date: 26-08-2010 Through 28-08-2010",

}

Wang, X, Liang, W & Zhang, L 2010, Morphable face reconstruction with multiple views. in Proceedings - 2010 2nd International Conference on Intelligent Human-Machine Systems and Cybernetics, IHMSC 2010., 5590895, Proceedings - 2010 2nd International Conference on Intelligent Human-Machine Systems and Cybernetics, IHMSC 2010, vol. 2, pp. 250-253, 2010 2nd International Conference on Intelligent Human-Machine Systems and Cybernetics, IHMSC 2010, Nanjing, China, 26/08/10. https://doi.org/10.1109/IHMSC.2010.163

Morphable face reconstruction with multiple views. / Wang, Xiaowen; Liang, Wei; Zhang, Liuxin.
Proceedings - 2010 2nd International Conference on Intelligent Human-Machine Systems and Cybernetics, IHMSC 2010. 2010. p. 250-253 5590895 (Proceedings - 2010 2nd International Conference on Intelligent Human-Machine Systems and Cybernetics, IHMSC 2010; Vol. 2).

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

TY - GEN

T1 - Morphable face reconstruction with multiple views

AU - Wang, Xiaowen

AU - Liang, Wei

AU - Zhang, Liuxin

PY - 2010

Y1 - 2010

N2 - The morphable modeling method of reconstructing 3D human face is based on a single given image, and the model fitting is ambiguous owing to the lack of depth information and geometry constraints between images. In this paper, we introduce a new face reconstruction method from multiple views based on the morphable model. The morphable face model is matched with multiple face images from different views. Using the multi-view geometry constraints, the ambiguity is efficiently eliminated and more realistic results are provided. We test our algorithm on the MPI face database and real images from our multi-camera system. The experimental results show the efficiency of the proposed method.

AB - The morphable modeling method of reconstructing 3D human face is based on a single given image, and the model fitting is ambiguous owing to the lack of depth information and geometry constraints between images. In this paper, we introduce a new face reconstruction method from multiple views based on the morphable model. The morphable face model is matched with multiple face images from different views. Using the multi-view geometry constraints, the ambiguity is efficiently eliminated and more realistic results are provided. We test our algorithm on the MPI face database and real images from our multi-camera system. The experimental results show the efficiency of the proposed method.

KW - 3D human face reconstruction

KW - Morphable model

KW - Multiple cameras

UR - http://www.scopus.com/inward/record.url?scp=78449284455&partnerID=8YFLogxK

U2 - 10.1109/IHMSC.2010.163

DO - 10.1109/IHMSC.2010.163

M3 - Conference contribution

AN - SCOPUS:78449284455

SN - 9780769541518

T3 - Proceedings - 2010 2nd International Conference on Intelligent Human-Machine Systems and Cybernetics, IHMSC 2010

SP - 250

EP - 253

BT - Proceedings - 2010 2nd International Conference on Intelligent Human-Machine Systems and Cybernetics, IHMSC 2010

T2 - 2010 2nd International Conference on Intelligent Human-Machine Systems and Cybernetics, IHMSC 2010

Y2 - 26 August 2010 through 28 August 2010

ER -

Morphable face reconstruction with multiple views

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this