Adaptive 3D face reconstruction from unconstrained photo collections

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

  • 16 Citations

Abstract

Given a collection of "in-the-wild" face images captured under a variety of unknown pose, expression, and illumination conditions, this paper presents a method for reconstructing a 3D face surface model of an individual along with albedo information. Motivated by the success of recent face reconstruction techniques on large photo collections, we extend prior work to adapt to low quality photo collections with fewer images. We achieve this by fitting a 3D Morphable Model to form a personalized template and developing a novel photometric stereo formulation, under a coarse-to-fine scheme. Superior experimental results are reported on synthetic and real-world photo collections.

LanguageEnglish (US)
Title of host publication2016 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2016
PublisherIEEE Computer Society
Pages4197-4206
Number of pages10
Volume2016-January
ISBN (Electronic)9781467388511
StatePublished - 2016
Event2016 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2016 - Las Vegas, United States
Duration: Jun 26 2016Jul 1 2016

Other

Other2016 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2016
CountryUnited States
CityLas Vegas
Period6/26/167/1/16

Profile

Lighting

ASJC Scopus subject areas

  • Software
  • Computer Vision and Pattern Recognition

Cite this

Roth, J., Tong, Y., & Liu, X. (2016). Adaptive 3D face reconstruction from unconstrained photo collections. In 2016 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2016 (Vol. 2016-January, pp. 4197-4206). IEEE Computer Society.

Adaptive 3D face reconstruction from unconstrained photo collections. / Roth, Joseph; Tong, Yiying; Liu, Xiaoming.

2016 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2016. Vol. 2016-January IEEE Computer Society, 2016. p. 4197-4206.

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

Roth, J, Tong, Y & Liu, X 2016, Adaptive 3D face reconstruction from unconstrained photo collections. in 2016 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2016. vol. 2016-January, IEEE Computer Society, pp. 4197-4206, 2016 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2016, Las Vegas, United States, 6/26/16.
Roth J, Tong Y, Liu X. Adaptive 3D face reconstruction from unconstrained photo collections. In 2016 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2016. Vol. 2016-January. IEEE Computer Society. 2016. p. 4197-4206.
Roth, Joseph ; Tong, Yiying ; Liu, Xiaoming. / Adaptive 3D face reconstruction from unconstrained photo collections. 2016 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2016. Vol. 2016-January IEEE Computer Society, 2016. pp. 4197-4206
@inproceedings{ed858d7b501e41b58395c84f0e23216c,
title = "Adaptive 3D face reconstruction from unconstrained photo collections",
abstract = "Given a collection of {"}in-the-wild{"} face images captured under a variety of unknown pose, expression, and illumination conditions, this paper presents a method for reconstructing a 3D face surface model of an individual along with albedo information. Motivated by the success of recent face reconstruction techniques on large photo collections, we extend prior work to adapt to low quality photo collections with fewer images. We achieve this by fitting a 3D Morphable Model to form a personalized template and developing a novel photometric stereo formulation, under a coarse-to-fine scheme. Superior experimental results are reported on synthetic and real-world photo collections.",
author = "Joseph Roth and Yiying Tong and Xiaoming Liu",
year = "2016",
language = "English (US)",
volume = "2016-January",
pages = "4197--4206",
booktitle = "2016 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2016",
publisher = "IEEE Computer Society",
address = "United States",

}

TY - GEN

T1 - Adaptive 3D face reconstruction from unconstrained photo collections

AU - Roth,Joseph

AU - Tong,Yiying

AU - Liu,Xiaoming

PY - 2016

Y1 - 2016

N2 - Given a collection of "in-the-wild" face images captured under a variety of unknown pose, expression, and illumination conditions, this paper presents a method for reconstructing a 3D face surface model of an individual along with albedo information. Motivated by the success of recent face reconstruction techniques on large photo collections, we extend prior work to adapt to low quality photo collections with fewer images. We achieve this by fitting a 3D Morphable Model to form a personalized template and developing a novel photometric stereo formulation, under a coarse-to-fine scheme. Superior experimental results are reported on synthetic and real-world photo collections.

AB - Given a collection of "in-the-wild" face images captured under a variety of unknown pose, expression, and illumination conditions, this paper presents a method for reconstructing a 3D face surface model of an individual along with albedo information. Motivated by the success of recent face reconstruction techniques on large photo collections, we extend prior work to adapt to low quality photo collections with fewer images. We achieve this by fitting a 3D Morphable Model to form a personalized template and developing a novel photometric stereo formulation, under a coarse-to-fine scheme. Superior experimental results are reported on synthetic and real-world photo collections.

UR - http://www.scopus.com/inward/record.url?scp=84986327444&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84986327444&partnerID=8YFLogxK

M3 - Conference contribution

VL - 2016-January

SP - 4197

EP - 4206

BT - 2016 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2016

PB - IEEE Computer Society

ER -