Abstract
We present a fully automatic pipeline to train 3D Mor-
phable Models (3DMMs), with contributions in pose nor-
malisation, dense correspondence using both shape and
texture information, and high quality, high resolution tex-
ture mapping. We propose a dense correspondence system,
combining a hierarchical parts-based template morphing
framework in the shape channel and a refining optical flow
in the texture channel. The texture map is generated us-
ing raw texture images from five views. We employ a pixel-
embedding method to maintain the texture map at the same
high resolution as the raw texture images, rather than us-
ing per-vertex color maps. The high quality texture map is
then used for statistical texture modelling. The Headspace
dataset used for training includes demographic information
about each subject, allowing for the construction of both
global 3DMMs and models tailored for specific gender and
age groups. We build both global craniofacial 3DMMs and
demographic sub-population 3DMMs from more than 1200
distinct identities. To our knowledge, we present the first
public 3DMM of the full human head in both shape and
texture: the Liverpool-York Head Model. Furthermore, we
analyse the 3DMMs in terms of a range of performance
metrics. Our evaluations reveal that the training pipeline
constructs state-of-the-art models.
phable Models (3DMMs), with contributions in pose nor-
malisation, dense correspondence using both shape and
texture information, and high quality, high resolution tex-
ture mapping. We propose a dense correspondence system,
combining a hierarchical parts-based template morphing
framework in the shape channel and a refining optical flow
in the texture channel. The texture map is generated us-
ing raw texture images from five views. We employ a pixel-
embedding method to maintain the texture map at the same
high resolution as the raw texture images, rather than us-
ing per-vertex color maps. The high quality texture map is
then used for statistical texture modelling. The Headspace
dataset used for training includes demographic information
about each subject, allowing for the construction of both
global 3DMMs and models tailored for specific gender and
age groups. We build both global craniofacial 3DMMs and
demographic sub-population 3DMMs from more than 1200
distinct identities. To our knowledge, we present the first
public 3DMM of the full human head in both shape and
texture: the Liverpool-York Head Model. Furthermore, we
analyse the 3DMMs in terms of a range of performance
metrics. Our evaluations reveal that the training pipeline
constructs state-of-the-art models.
Original language | English |
---|---|
Title of host publication | Proceedings - 2017 IEEE International Conference on Computer Vision, ICCV 2017 |
Pages | 3104-3112 |
Number of pages | 9 |
Volume | 2017-October |
ISBN (Electronic) | 9781538610329 |
DOIs | |
Publication status | Published - 25 Dec 2017 |
Publication series
Name | Title Proceedings / IEEE International Conference on Computer Vision. |
---|---|
Publisher | IEEE |
ISSN (Print) | 2380-7504 |
Bibliographical note
© 2017, IEEE. This is an author-produced version of the published paper. Uploaded in accordance with the publisher’s self-archiving policy. Further copying may not be permitted; contact the publisher for detailsKeywords
- 3D Morphabe Model; 3D shape registration; 3D imaging