Expressive facial subspace construction from key face selection

Ryo Takamizawa; Takanori Suzuki; Hiroyuki Kubo; Akinobu Maejima; Shigeo Morishima

doi:10.1145/1599301.1599308

Expressive facial subspace construction from key face selection

Ryo Takamizawa^*, Takanori Suzuki, Hiroyuki Kubo, Akinobu Maejima, Shigeo Morishima

^*Corresponding author for this work

School of Advanced Science and Engineering

Research output: Contribution to conference › Paper › peer-review

1 Citation (Scopus)

Abstract

MoCap-based facial expression synthesis techniques have been applied to provide CG character with expressive and accurate facial expressions [Deng et al. 2006: Lau et al. 2007]. The representative performance of these techniques depends on the variety of captured facial expressions. It is also difficult to guess what expressions are needed to synthesize expressive face before capture. Therefore, much MoCap data are required to construct a subspace employing dimensional compression techniques, and then the space enables us to synthesize expressions with linear-combination of basis vectors of the space. However, it is hard work to take much facial MoCap data to obtain expressive result.

Original language	English
DOIs	https://doi.org/10.1145/1599301.1599308
Publication status	Published - 2009
Event	SIGGRAPH 2009: Posters, SIGGRAPH '09 - New Orleans, LA, United States Duration: 2009 Aug 3 → 2009 Aug 7

Conference

Conference	SIGGRAPH 2009: Posters, SIGGRAPH '09
Country/Territory	United States
City	New Orleans, LA
Period	09/8/3 → 09/8/7

ASJC Scopus subject areas

Computer Graphics and Computer-Aided Design
Human-Computer Interaction
Software

Access to Document

10.1145/1599301.1599308

Cite this

@conference{f97d7648453442d0b24eb27c21d381f1,

title = "Expressive facial subspace construction from key face selection",

abstract = "MoCap-based facial expression synthesis techniques have been applied to provide CG character with expressive and accurate facial expressions [Deng et al. 2006: Lau et al. 2007]. The representative performance of these techniques depends on the variety of captured facial expressions. It is also difficult to guess what expressions are needed to synthesize expressive face before capture. Therefore, much MoCap data are required to construct a subspace employing dimensional compression techniques, and then the space enables us to synthesize expressions with linear-combination of basis vectors of the space. However, it is hard work to take much facial MoCap data to obtain expressive result.",

author = "Ryo Takamizawa and Takanori Suzuki and Hiroyuki Kubo and Akinobu Maejima and Shigeo Morishima",

year = "2009",

doi = "10.1145/1599301.1599308",

language = "English",

note = "SIGGRAPH 2009: Posters, SIGGRAPH '09 ; Conference date: 03-08-2009 Through 07-08-2009",

}

TY - CONF

T1 - Expressive facial subspace construction from key face selection

AU - Takamizawa, Ryo

AU - Suzuki, Takanori

AU - Kubo, Hiroyuki

AU - Maejima, Akinobu

AU - Morishima, Shigeo

PY - 2009

Y1 - 2009

N2 - MoCap-based facial expression synthesis techniques have been applied to provide CG character with expressive and accurate facial expressions [Deng et al. 2006: Lau et al. 2007]. The representative performance of these techniques depends on the variety of captured facial expressions. It is also difficult to guess what expressions are needed to synthesize expressive face before capture. Therefore, much MoCap data are required to construct a subspace employing dimensional compression techniques, and then the space enables us to synthesize expressions with linear-combination of basis vectors of the space. However, it is hard work to take much facial MoCap data to obtain expressive result.

AB - MoCap-based facial expression synthesis techniques have been applied to provide CG character with expressive and accurate facial expressions [Deng et al. 2006: Lau et al. 2007]. The representative performance of these techniques depends on the variety of captured facial expressions. It is also difficult to guess what expressions are needed to synthesize expressive face before capture. Therefore, much MoCap data are required to construct a subspace employing dimensional compression techniques, and then the space enables us to synthesize expressions with linear-combination of basis vectors of the space. However, it is hard work to take much facial MoCap data to obtain expressive result.

UR - http://www.scopus.com/inward/record.url?scp=73049106385&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=73049106385&partnerID=8YFLogxK

U2 - 10.1145/1599301.1599308

DO - 10.1145/1599301.1599308

M3 - Paper

AN - SCOPUS:73049106385

T2 - SIGGRAPH 2009: Posters, SIGGRAPH '09

Y2 - 3 August 2009 through 7 August 2009

ER -

Expressive facial subspace construction from key face selection

Abstract

Conference

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this