Enhanced waters 2D muscle model for facial expression generation

Dinesh Kumar, Dharmendra Sharma

Research output: A Conference proceeding or a Chapter in BookConference contribution

Abstract

In this paper we present an improved Waters facial model used as an avatar for work published in (Kumar and Vanualailai, 2016), which described a Facial Animation System driven by the Facial Action Coding System (FACS) in a low-bandwidth video streaming setting. FACS defines 32 single Action Units (AUs) which are generated by an underlying muscle action that interact in different ways to create facial expressions. Because FACS AU describes atomic facial distortions using facial muscles, a face model that can allow AU mappings to be applied directly on the respective muscles is desirable. Hence for this task we choose the Waters anatomy-based face model due to its simplicity and implementation of pseudo muscles. However Waters face model is limited in its ability to create realistic expressions mainly the lack of a function to represent sheet muscles, unrealistic jaw rotation function and improper implementation of sphincter muscles. Therefore in this work we provide enhancements to the Waters facial model by improving its UI, adding sheet muscles, providing an alternative implementation to the jaw rotation function, presenting a new sphincter muscle model that can be used around the eyes and changes to operation of the sphincter muscle used around the mouth.

Original languageEnglish
Title of host publicationVISIGRAPP 2019 - Proceedings of the 14th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications
EditorsAndreas Kerren, Christophe Hurter, Jose Braz
PublisherScitepress
Pages262-269
Number of pages8
Volume1
ISBN (Electronic)9789897583544
ISBN (Print)9789897583544
DOIs
Publication statusPublished - 2019
Event14th International Conference on Computer Graphics Theory and Applications, GRAPP 2019 - Part of the 14th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications, VISIGRAPP 2019 - Prague, Czech Republic
Duration: 25 Feb 201927 Feb 2019

Publication series

NameVISIGRAPP 2019 - Proceedings of the 14th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications
Volume1

Conference

Conference14th International Conference on Computer Graphics Theory and Applications, GRAPP 2019 - Part of the 14th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications, VISIGRAPP 2019
CountryCzech Republic
CityPrague
Period25/02/1927/02/19

Fingerprint

Muscle
Water
Video streaming
Animation
Bandwidth

Cite this

Kumar, D., & Sharma, D. (2019). Enhanced waters 2D muscle model for facial expression generation. In A. Kerren, C. Hurter, & J. Braz (Eds.), VISIGRAPP 2019 - Proceedings of the 14th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (Vol. 1, pp. 262-269). (VISIGRAPP 2019 - Proceedings of the 14th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications; Vol. 1). Scitepress. https://doi.org/10.5220/0007379302620269, https://doi.org/10.5220/0007379302620269
Kumar, Dinesh ; Sharma, Dharmendra. / Enhanced waters 2D muscle model for facial expression generation. VISIGRAPP 2019 - Proceedings of the 14th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications. editor / Andreas Kerren ; Christophe Hurter ; Jose Braz. Vol. 1 Scitepress, 2019. pp. 262-269 (VISIGRAPP 2019 - Proceedings of the 14th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications).
@inproceedings{569eebdd85434ab7b94f895a5003b6e0,
title = "Enhanced waters 2D muscle model for facial expression generation",
abstract = "In this paper we present an improved Waters facial model used as an avatar for work published in (Kumar and Vanualailai, 2016), which described a Facial Animation System driven by the Facial Action Coding System (FACS) in a low-bandwidth video streaming setting. FACS defines 32 single Action Units (AUs) which are generated by an underlying muscle action that interact in different ways to create facial expressions. Because FACS AU describes atomic facial distortions using facial muscles, a face model that can allow AU mappings to be applied directly on the respective muscles is desirable. Hence for this task we choose the Waters anatomy-based face model due to its simplicity and implementation of pseudo muscles. However Waters face model is limited in its ability to create realistic expressions mainly the lack of a function to represent sheet muscles, unrealistic jaw rotation function and improper implementation of sphincter muscles. Therefore in this work we provide enhancements to the Waters facial model by improving its UI, adding sheet muscles, providing an alternative implementation to the jaw rotation function, presenting a new sphincter muscle model that can be used around the eyes and changes to operation of the sphincter muscle used around the mouth.",
keywords = "Facial Animation, Facial Expression, FACS, Muscle Model, Physics-based Model",
author = "Dinesh Kumar and Dharmendra Sharma",
year = "2019",
doi = "10.5220/0007379302620269",
language = "English",
isbn = "9789897583544",
volume = "1",
series = "VISIGRAPP 2019 - Proceedings of the 14th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications",
publisher = "Scitepress",
pages = "262--269",
editor = "Andreas Kerren and Christophe Hurter and Jose Braz",
booktitle = "VISIGRAPP 2019 - Proceedings of the 14th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications",

}

Kumar, D & Sharma, D 2019, Enhanced waters 2D muscle model for facial expression generation. in A Kerren, C Hurter & J Braz (eds), VISIGRAPP 2019 - Proceedings of the 14th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications. vol. 1, VISIGRAPP 2019 - Proceedings of the 14th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications, vol. 1, Scitepress, pp. 262-269, 14th International Conference on Computer Graphics Theory and Applications, GRAPP 2019 - Part of the 14th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications, VISIGRAPP 2019, Prague, Czech Republic, 25/02/19. https://doi.org/10.5220/0007379302620269, https://doi.org/10.5220/0007379302620269

Enhanced waters 2D muscle model for facial expression generation. / Kumar, Dinesh; Sharma, Dharmendra.

VISIGRAPP 2019 - Proceedings of the 14th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications. ed. / Andreas Kerren; Christophe Hurter; Jose Braz. Vol. 1 Scitepress, 2019. p. 262-269 (VISIGRAPP 2019 - Proceedings of the 14th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications; Vol. 1).

Research output: A Conference proceeding or a Chapter in BookConference contribution

TY - GEN

T1 - Enhanced waters 2D muscle model for facial expression generation

AU - Kumar, Dinesh

AU - Sharma, Dharmendra

PY - 2019

Y1 - 2019

N2 - In this paper we present an improved Waters facial model used as an avatar for work published in (Kumar and Vanualailai, 2016), which described a Facial Animation System driven by the Facial Action Coding System (FACS) in a low-bandwidth video streaming setting. FACS defines 32 single Action Units (AUs) which are generated by an underlying muscle action that interact in different ways to create facial expressions. Because FACS AU describes atomic facial distortions using facial muscles, a face model that can allow AU mappings to be applied directly on the respective muscles is desirable. Hence for this task we choose the Waters anatomy-based face model due to its simplicity and implementation of pseudo muscles. However Waters face model is limited in its ability to create realistic expressions mainly the lack of a function to represent sheet muscles, unrealistic jaw rotation function and improper implementation of sphincter muscles. Therefore in this work we provide enhancements to the Waters facial model by improving its UI, adding sheet muscles, providing an alternative implementation to the jaw rotation function, presenting a new sphincter muscle model that can be used around the eyes and changes to operation of the sphincter muscle used around the mouth.

AB - In this paper we present an improved Waters facial model used as an avatar for work published in (Kumar and Vanualailai, 2016), which described a Facial Animation System driven by the Facial Action Coding System (FACS) in a low-bandwidth video streaming setting. FACS defines 32 single Action Units (AUs) which are generated by an underlying muscle action that interact in different ways to create facial expressions. Because FACS AU describes atomic facial distortions using facial muscles, a face model that can allow AU mappings to be applied directly on the respective muscles is desirable. Hence for this task we choose the Waters anatomy-based face model due to its simplicity and implementation of pseudo muscles. However Waters face model is limited in its ability to create realistic expressions mainly the lack of a function to represent sheet muscles, unrealistic jaw rotation function and improper implementation of sphincter muscles. Therefore in this work we provide enhancements to the Waters facial model by improving its UI, adding sheet muscles, providing an alternative implementation to the jaw rotation function, presenting a new sphincter muscle model that can be used around the eyes and changes to operation of the sphincter muscle used around the mouth.

KW - Facial Animation

KW - Facial Expression

KW - FACS

KW - Muscle Model

KW - Physics-based Model

UR - http://www.scopus.com/inward/record.url?scp=85068239317&partnerID=8YFLogxK

U2 - 10.5220/0007379302620269

DO - 10.5220/0007379302620269

M3 - Conference contribution

SN - 9789897583544

VL - 1

T3 - VISIGRAPP 2019 - Proceedings of the 14th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications

SP - 262

EP - 269

BT - VISIGRAPP 2019 - Proceedings of the 14th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications

A2 - Kerren, Andreas

A2 - Hurter, Christophe

A2 - Braz, Jose

PB - Scitepress

ER -

Kumar D, Sharma D. Enhanced waters 2D muscle model for facial expression generation. In Kerren A, Hurter C, Braz J, editors, VISIGRAPP 2019 - Proceedings of the 14th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications. Vol. 1. Scitepress. 2019. p. 262-269. (VISIGRAPP 2019 - Proceedings of the 14th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications). https://doi.org/10.5220/0007379302620269, https://doi.org/10.5220/0007379302620269