3D Face Morphable Models “In-the-Wild”

File Description SizeFormat 
0025 (1).pdfAccepted version5.05 MBAdobe PDFView/Open
Title: 3D Face Morphable Models “In-the-Wild”
Authors: Booth, J
Antonakos, E
Ploumpis, S
Trigeorgis, G
Panagakis, Y
Zafeiriou, S
Item Type: Conference Paper
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 sin- gle images. With the advent of new 3D sensors, many 3D fa- cial 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 illu- mination parameters. Furthermore, we propose a new fast algorithm for fitting the 3DMM in arbitrary images. Fi- nally, we have captured the first 3D facial database with relatively unconstrained conditions and report quantitative evaluations with state-of-the-art performance. Complemen- tary qualitative reconstruction results are demonstrated on standard “in-the-wild” facial databases.
Issue Date: 9-Nov-2017
Date of Acceptance: 3-Mar-2017
URI: http://hdl.handle.net/10044/1/69914
DOI: https://dx.doi.org/10.1109/CVPR.2017.580
Publisher: IEEE
Replaces: http://hdl.handle.net/10044/1/45421
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.
Sponsor/Funder: Engineering & Physical Science Research Council (E
Commission of the European Communities
Funder's Grant Number: EP/N007743/1
Conference Name: IEEE International Conference on Computer Vision and Pattern Recognition
Publication Status: Published
Start Date: 2017-07-21
Finish Date: 2017-07-26
Conference Place: Hawaii, USA
Appears in Collections:Faculty of Engineering

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.

Creative Commonsx