A probabilistic approach to realistic face synthesis

Hyunjung Shim, Inwoo Ha, Taehyun Rhee, James Dokyoon Kim, Changyeong Kim

Research output: Chapter in Book/Report/Conference proceedingConference contribution

4 Citations (Scopus)

Abstract

This paper presents a novel approach to face modeling for realistic synthesis, powered by a probabilistic face diffuse model and a generic face specular map. We first construct a probabilistic face diffuse model for estimating the albedo and the normals of a face from an unknown input image. Then, we introduce a generic face specular map for estimating the specularity of the face. Using the estimated albedo, normal and specular information, we can synthesize the face under arbitrary lighting and viewing directions realistically. Unlike many existing face modeling techniques, our approach can retain both the diffuse and specular properties of the face without involving an elaborating 3D matching procedure. Thanks to the compact representation and the effective inference scheme, our technique can be applied to many practical applications, such as face normalization, avatar creation and de-identification.

Original languageEnglish
Title of host publication2010 IEEE International Conference on Image Processing, ICIP 2010 - Proceedings
Pages1817-1820
Number of pages4
DOIs
Publication statusPublished - 2010 Dec 1
Event2010 17th IEEE International Conference on Image Processing, ICIP 2010 - Hong Kong, Hong Kong
Duration: 2010 Sep 262010 Sep 29

Other

Other2010 17th IEEE International Conference on Image Processing, ICIP 2010
CountryHong Kong
CityHong Kong
Period10/9/2610/9/29

Fingerprint

Lighting

All Science Journal Classification (ASJC) codes

  • Software
  • Computer Vision and Pattern Recognition
  • Signal Processing

Cite this

Shim, H., Ha, I., Rhee, T., Kim, J. D., & Kim, C. (2010). A probabilistic approach to realistic face synthesis. In 2010 IEEE International Conference on Image Processing, ICIP 2010 - Proceedings (pp. 1817-1820). [5653024] https://doi.org/10.1109/ICIP.2010.5653024
Shim, Hyunjung ; Ha, Inwoo ; Rhee, Taehyun ; Kim, James Dokyoon ; Kim, Changyeong. / A probabilistic approach to realistic face synthesis. 2010 IEEE International Conference on Image Processing, ICIP 2010 - Proceedings. 2010. pp. 1817-1820
@inproceedings{cba5b55fc250483bbb5391c69c6e393f,
title = "A probabilistic approach to realistic face synthesis",
abstract = "This paper presents a novel approach to face modeling for realistic synthesis, powered by a probabilistic face diffuse model and a generic face specular map. We first construct a probabilistic face diffuse model for estimating the albedo and the normals of a face from an unknown input image. Then, we introduce a generic face specular map for estimating the specularity of the face. Using the estimated albedo, normal and specular information, we can synthesize the face under arbitrary lighting and viewing directions realistically. Unlike many existing face modeling techniques, our approach can retain both the diffuse and specular properties of the face without involving an elaborating 3D matching procedure. Thanks to the compact representation and the effective inference scheme, our technique can be applied to many practical applications, such as face normalization, avatar creation and de-identification.",
author = "Hyunjung Shim and Inwoo Ha and Taehyun Rhee and Kim, {James Dokyoon} and Changyeong Kim",
year = "2010",
month = "12",
day = "1",
doi = "10.1109/ICIP.2010.5653024",
language = "English",
isbn = "9781424479948",
pages = "1817--1820",
booktitle = "2010 IEEE International Conference on Image Processing, ICIP 2010 - Proceedings",

}

Shim, H, Ha, I, Rhee, T, Kim, JD & Kim, C 2010, A probabilistic approach to realistic face synthesis. in 2010 IEEE International Conference on Image Processing, ICIP 2010 - Proceedings., 5653024, pp. 1817-1820, 2010 17th IEEE International Conference on Image Processing, ICIP 2010, Hong Kong, Hong Kong, 10/9/26. https://doi.org/10.1109/ICIP.2010.5653024

A probabilistic approach to realistic face synthesis. / Shim, Hyunjung; Ha, Inwoo; Rhee, Taehyun; Kim, James Dokyoon; Kim, Changyeong.

2010 IEEE International Conference on Image Processing, ICIP 2010 - Proceedings. 2010. p. 1817-1820 5653024.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - A probabilistic approach to realistic face synthesis

AU - Shim, Hyunjung

AU - Ha, Inwoo

AU - Rhee, Taehyun

AU - Kim, James Dokyoon

AU - Kim, Changyeong

PY - 2010/12/1

Y1 - 2010/12/1

N2 - This paper presents a novel approach to face modeling for realistic synthesis, powered by a probabilistic face diffuse model and a generic face specular map. We first construct a probabilistic face diffuse model for estimating the albedo and the normals of a face from an unknown input image. Then, we introduce a generic face specular map for estimating the specularity of the face. Using the estimated albedo, normal and specular information, we can synthesize the face under arbitrary lighting and viewing directions realistically. Unlike many existing face modeling techniques, our approach can retain both the diffuse and specular properties of the face without involving an elaborating 3D matching procedure. Thanks to the compact representation and the effective inference scheme, our technique can be applied to many practical applications, such as face normalization, avatar creation and de-identification.

AB - This paper presents a novel approach to face modeling for realistic synthesis, powered by a probabilistic face diffuse model and a generic face specular map. We first construct a probabilistic face diffuse model for estimating the albedo and the normals of a face from an unknown input image. Then, we introduce a generic face specular map for estimating the specularity of the face. Using the estimated albedo, normal and specular information, we can synthesize the face under arbitrary lighting and viewing directions realistically. Unlike many existing face modeling techniques, our approach can retain both the diffuse and specular properties of the face without involving an elaborating 3D matching procedure. Thanks to the compact representation and the effective inference scheme, our technique can be applied to many practical applications, such as face normalization, avatar creation and de-identification.

UR - http://www.scopus.com/inward/record.url?scp=78651097536&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=78651097536&partnerID=8YFLogxK

U2 - 10.1109/ICIP.2010.5653024

DO - 10.1109/ICIP.2010.5653024

M3 - Conference contribution

SN - 9781424479948

SP - 1817

EP - 1820

BT - 2010 IEEE International Conference on Image Processing, ICIP 2010 - Proceedings

ER -

Shim H, Ha I, Rhee T, Kim JD, Kim C. A probabilistic approach to realistic face synthesis. In 2010 IEEE International Conference on Image Processing, ICIP 2010 - Proceedings. 2010. p. 1817-1820. 5653024 https://doi.org/10.1109/ICIP.2010.5653024