3D face morphable models "In-The-Wild"

Conference paper


Booth, J., Antonakos, E., Ploumpis, S., Trigeorgis, G., Panagakis, Y. and Zafeiriou, S. 2017. 3D face morphable models "In-The-Wild". 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Honolulu, HI, USA 21 - 26 Jul 2017 Institute of Electrical and Electronics Engineers (IEEE). pp. 5464-5473 https://doi.org/10.1109/CVPR.2017.580
TypeConference paper
Title3D face morphable models "In-The-Wild"
AuthorsBooth, J., Antonakos, E., Ploumpis, S., Trigeorgis, G., Panagakis, Y. and Zafeiriou, S.
Abstract

3D Morphable Models (3DMMs) are powerful statistical models of 3D facial shape and texture, and among the state-of-the-art methods for reconstructing facial shape from single images. With the advent of new 3D sensors, many 3D facial datasets have been collected containing both neutral as well as expressive faces. However, all datasets are captured under controlled conditions. Thus, even though powerful 3D facial shape models can be learnt from such data, it is difficult to build statistical texture models that are sufficient to reconstruct faces captured in unconstrained conditions (in-the-wild). In this paper, we propose the first, to the best of our knowledge, in-the-wild 3DMM by combining a powerful statistical model of facial shape, which describes both identity and expression, with an in-the-wild texture model. We show that the employment of such an in-the-wild texture model greatly simplifies the fitting procedure, because there is no need to optimise with regards to the illumination parameters. Furthermore, we propose a new fast algorithm for fitting the 3DMM in arbitrary images. Finally, we have captured the first 3D facial database with relatively unconstrained conditions and report quantitative evaluations with state-of-the-art performance. Complementary qualitative reconstruction results are demonstrated on standard in-the-wild facial databases.

LanguageEnglish
Conference2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
Page range5464-5473
ISSN1063-6919
ISBN
Hardcover9781538604571
PublisherInstitute of Electrical and Electronics Engineers (IEEE)
Publication dates
Print26 Jul 2017
Online09 Nov 2017
Publication process dates
Deposited07 Mar 2018
Accepted03 Mar 2017
Output statusPublished
Accepted author manuscript
Copyright Statement

© 2017 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works

Digital Object Identifier (DOI)https://doi.org/10.1109/CVPR.2017.580
Book titleThe 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
Permalink -

https://repository.mdx.ac.uk/item/87879

Download files


Accepted author manuscript
  • 10
    total views
  • 0
    total downloads
  • 2
    views this month
  • 0
    downloads this month

Export as