Generating 3D Morphable Model parameters for facial tracking: Factorising identity and expression

Alexander Davies; Carl Henrik Ek; C Dalton; N Campbell

Generating 3D Morphable Model parameters for facial tracking: Factorising identity and expression

Alexander Davies, Carl Henrik Ek, C Dalton, N Campbell

Research output: Chapter in Book/Report/Conference proceeding › Conference Contribution (Conference Proceeding)

3 Citations (Scopus)

Abstract

The ability to factorise parameters into identity and expression parameters is highly desirable in facial tracking as it requires only the identity parameters to be set in the initial frame leaving the expression parameters to be adjusted in subsequent frames. In this paper we introduce a strategy for creating parameters for a data-driven 3D Morphable Model (3DMM) which are able to separately model the variance due to identity and expression found in the training data. We present three factorisation schemes and evaluate their appropriateness for tracking by comparing the variances between the identity coefficients and expression coefficients when fitted to data of individuals performing different facial expressions.

Original language	English
Title of host publication	IVAPP 2012 - Proceedings of the International Conference on Computer Graphics Theory and Applications and International Conference on Information Visualization Theory and Applications
Editors	Paul Richard, Martin Kraus, Robert S. Laramee, José Braz
Publisher	SciTePress
Pages	309-318
Number of pages	10
ISBN (Print)	9789898565020
Publication status	Published - 2012

Keywords

3D morphable models, Facial animation, PCA, Tracking

Access to Document

http://dblp.uni-trier.de/db/conf/grapp/grapp2012.html#DaviesEDC12

Handle.net

Persistent link

Cite this

Davies, A., Ek, C. H., Dalton, C., & Campbell, N. (2012). Generating 3D Morphable Model parameters for facial tracking: Factorising identity and expression. In P. Richard, M. Kraus, R. S. Laramee, & J. Braz (Eds.), IVAPP 2012 - Proceedings of the International Conference on Computer Graphics Theory and Applications and International Conference on Information Visualization Theory and Applications (pp. 309-318). SciTePress. http://dblp.uni-trier.de/db/conf/grapp/grapp2012.html#DaviesEDC12

Davies, Alexander ; Ek, Carl Henrik ; Dalton, C et al. / Generating 3D Morphable Model parameters for facial tracking : Factorising identity and expression. IVAPP 2012 - Proceedings of the International Conference on Computer Graphics Theory and Applications and International Conference on Information Visualization Theory and Applications. editor / Paul Richard ; Martin Kraus ; Robert S. Laramee ; José Braz. SciTePress, 2012. pp. 309-318

@inproceedings{0d114f3543254342a425a1f1107101b5,

title = "Generating 3D Morphable Model parameters for facial tracking: Factorising identity and expression",

abstract = "The ability to factorise parameters into identity and expression parameters is highly desirable in facial tracking as it requires only the identity parameters to be set in the initial frame leaving the expression parameters to be adjusted in subsequent frames. In this paper we introduce a strategy for creating parameters for a data-driven 3D Morphable Model (3DMM) which are able to separately model the variance due to identity and expression found in the training data. We present three factorisation schemes and evaluate their appropriateness for tracking by comparing the variances between the identity coefficients and expression coefficients when fitted to data of individuals performing different facial expressions.",

keywords = "3D morphable models, Facial animation, PCA, Tracking",

author = "Alexander Davies and Ek, {Carl Henrik} and C Dalton and N Campbell",

year = "2012",

language = "English",

isbn = "9789898565020",

pages = "309--318",

editor = "Paul Richard and Martin Kraus and Laramee, {Robert S.} and Jos{\'e} Braz",

booktitle = "IVAPP 2012 - Proceedings of the International Conference on Computer Graphics Theory and Applications and International Conference on Information Visualization Theory and Applications",

publisher = "SciTePress",

}

Davies, A, Ek, CH, Dalton, C & Campbell, N 2012, Generating 3D Morphable Model parameters for facial tracking: Factorising identity and expression. in P Richard, M Kraus, RS Laramee & J Braz (eds), IVAPP 2012 - Proceedings of the International Conference on Computer Graphics Theory and Applications and International Conference on Information Visualization Theory and Applications. SciTePress, pp. 309-318. <http://dblp.uni-trier.de/db/conf/grapp/grapp2012.html#DaviesEDC12>

Generating 3D Morphable Model parameters for facial tracking : Factorising identity and expression. / Davies, Alexander; Ek, Carl Henrik; Dalton, C et al.

IVAPP 2012 - Proceedings of the International Conference on Computer Graphics Theory and Applications and International Conference on Information Visualization Theory and Applications. ed. / Paul Richard; Martin Kraus; Robert S. Laramee; José Braz. SciTePress, 2012. p. 309-318.

Research output: Chapter in Book/Report/Conference proceeding › Conference Contribution (Conference Proceeding)

TY - GEN

T1 - Generating 3D Morphable Model parameters for facial tracking

T2 - Factorising identity and expression

AU - Davies, Alexander

AU - Ek, Carl Henrik

AU - Dalton, C

AU - Campbell, N

PY - 2012

Y1 - 2012

N2 - The ability to factorise parameters into identity and expression parameters is highly desirable in facial tracking as it requires only the identity parameters to be set in the initial frame leaving the expression parameters to be adjusted in subsequent frames. In this paper we introduce a strategy for creating parameters for a data-driven 3D Morphable Model (3DMM) which are able to separately model the variance due to identity and expression found in the training data. We present three factorisation schemes and evaluate their appropriateness for tracking by comparing the variances between the identity coefficients and expression coefficients when fitted to data of individuals performing different facial expressions.

AB - The ability to factorise parameters into identity and expression parameters is highly desirable in facial tracking as it requires only the identity parameters to be set in the initial frame leaving the expression parameters to be adjusted in subsequent frames. In this paper we introduce a strategy for creating parameters for a data-driven 3D Morphable Model (3DMM) which are able to separately model the variance due to identity and expression found in the training data. We present three factorisation schemes and evaluate their appropriateness for tracking by comparing the variances between the identity coefficients and expression coefficients when fitted to data of individuals performing different facial expressions.

KW - 3D morphable models, Facial animation, PCA, Tracking

M3 - Conference Contribution (Conference Proceeding)

SN - 9789898565020

SP - 309

EP - 318

BT - IVAPP 2012 - Proceedings of the International Conference on Computer Graphics Theory and Applications and International Conference on Information Visualization Theory and Applications

A2 - Richard, Paul

A2 - Kraus, Martin

A2 - Laramee, Robert S.

A2 - Braz, José

PB - SciTePress

ER -

Davies A, Ek CH, Dalton C, Campbell N. Generating 3D Morphable Model parameters for facial tracking: Factorising identity and expression. In Richard P, Kraus M, Laramee RS, Braz J, editors, IVAPP 2012 - Proceedings of the International Conference on Computer Graphics Theory and Applications and International Conference on Information Visualization Theory and Applications. SciTePress. 2012. p. 309-318

Generating 3D Morphable Model parameters for facial tracking: Factorising identity and expression

Abstract

Keywords

Access to Document

Handle.net

Fingerprint

Cite this