A generative model of worldwide facial appearance

Zachary Bessinger; Nathan Jacobs

doi:10.1109/WACV.2019.00172

A generative model of worldwide facial appearance

Zachary Bessinger, Nathan Jacobs

Computer Science

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

5 Scopus citations

Abstract

Human appearance depends on many proximate factors, including age, gender, ethnicity, and personal style choices. In this work, we model the relationship between human appearance and geographic location, which can impact these factors in complex ways. We propose GPS2Face, a dual-component generative network architecture that enables flexible facial generation with fine-grained control of latent factors. We use facial landmarks as a guide to synthesize likely faces for locations around in the world. We train our model on a large-scale dataset of geotagged faces and evaluate our proposed model, both qualitatively and quantitatively, against previous work.

Original language	English
Title of host publication	Proceedings - 2019 IEEE Winter Conference on Applications of Computer Vision, WACV 2019
Pages	1569-1578
Number of pages	10
ISBN (Electronic)	9781728119755
DOIs	https://doi.org/10.1109/WACV.2019.00172
State	Published - Mar 4 2019
Event	19th IEEE Winter Conference on Applications of Computer Vision, WACV 2019 - Waikoloa Village, United States Duration: Jan 7 2019 → Jan 11 2019

Publication series

Name	Proceedings - 2019 IEEE Winter Conference on Applications of Computer Vision, WACV 2019

Conference

Conference	19th IEEE Winter Conference on Applications of Computer Vision, WACV 2019
Country/Territory	United States
City	Waikoloa Village
Period	1/7/19 → 1/11/19

Bibliographical note

Publisher Copyright:
© 2019 IEEE

ASJC Scopus subject areas

Computer Vision and Pattern Recognition
Computer Science Applications

Access to Document

10.1109/WACV.2019.00172

Cite this

@inproceedings{b08250795d0f4b6489f21f4919cd58e5,

title = "A generative model of worldwide facial appearance",

abstract = "Human appearance depends on many proximate factors, including age, gender, ethnicity, and personal style choices. In this work, we model the relationship between human appearance and geographic location, which can impact these factors in complex ways. We propose GPS2Face, a dual-component generative network architecture that enables flexible facial generation with fine-grained control of latent factors. We use facial landmarks as a guide to synthesize likely faces for locations around in the world. We train our model on a large-scale dataset of geotagged faces and evaluate our proposed model, both qualitatively and quantitatively, against previous work.",

author = "Zachary Bessinger and Nathan Jacobs",

note = "Publisher Copyright: {\textcopyright} 2019 IEEE; 19th IEEE Winter Conference on Applications of Computer Vision, WACV 2019 ; Conference date: 07-01-2019 Through 11-01-2019",

year = "2019",

month = mar,

day = "4",

doi = "10.1109/WACV.2019.00172",

language = "English",

series = "Proceedings - 2019 IEEE Winter Conference on Applications of Computer Vision, WACV 2019",

pages = "1569--1578",

booktitle = "Proceedings - 2019 IEEE Winter Conference on Applications of Computer Vision, WACV 2019",

}

Bessinger, Z & Jacobs, N 2019, A generative model of worldwide facial appearance. in Proceedings - 2019 IEEE Winter Conference on Applications of Computer Vision, WACV 2019., 8658761, Proceedings - 2019 IEEE Winter Conference on Applications of Computer Vision, WACV 2019, pp. 1569-1578, 19th IEEE Winter Conference on Applications of Computer Vision, WACV 2019, Waikoloa Village, United States, 1/7/19. https://doi.org/10.1109/WACV.2019.00172

A generative model of worldwide facial appearance. / Bessinger, Zachary; Jacobs, Nathan.
Proceedings - 2019 IEEE Winter Conference on Applications of Computer Vision, WACV 2019. 2019. p. 1569-1578 8658761 (Proceedings - 2019 IEEE Winter Conference on Applications of Computer Vision, WACV 2019).

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

TY - GEN

T1 - A generative model of worldwide facial appearance

AU - Bessinger, Zachary

AU - Jacobs, Nathan

PY - 2019/3/4

Y1 - 2019/3/4

N2 - Human appearance depends on many proximate factors, including age, gender, ethnicity, and personal style choices. In this work, we model the relationship between human appearance and geographic location, which can impact these factors in complex ways. We propose GPS2Face, a dual-component generative network architecture that enables flexible facial generation with fine-grained control of latent factors. We use facial landmarks as a guide to synthesize likely faces for locations around in the world. We train our model on a large-scale dataset of geotagged faces and evaluate our proposed model, both qualitatively and quantitatively, against previous work.

AB - Human appearance depends on many proximate factors, including age, gender, ethnicity, and personal style choices. In this work, we model the relationship between human appearance and geographic location, which can impact these factors in complex ways. We propose GPS2Face, a dual-component generative network architecture that enables flexible facial generation with fine-grained control of latent factors. We use facial landmarks as a guide to synthesize likely faces for locations around in the world. We train our model on a large-scale dataset of geotagged faces and evaluate our proposed model, both qualitatively and quantitatively, against previous work.

UR - http://www.scopus.com/inward/record.url?scp=85063586677&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85063586677&partnerID=8YFLogxK

U2 - 10.1109/WACV.2019.00172

DO - 10.1109/WACV.2019.00172

M3 - Conference contribution

AN - SCOPUS:85063586677

T3 - Proceedings - 2019 IEEE Winter Conference on Applications of Computer Vision, WACV 2019

SP - 1569

EP - 1578

BT - Proceedings - 2019 IEEE Winter Conference on Applications of Computer Vision, WACV 2019

T2 - 19th IEEE Winter Conference on Applications of Computer Vision, WACV 2019

Y2 - 7 January 2019 through 11 January 2019

ER -

A generative model of worldwide facial appearance

Abstract

Publication series

Conference

Bibliographical note

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this