Practical and scalable desktop-based high-quality facial capture
File(s)ECCV2022-desktopfacecapture.pdf (4.48 MB)
Accepted version
Author(s)
Type
Conference Paper
Abstract
We present a novel desktop-based system for high-quality
facial capture including geometry and facial appearance. The proposed
acquisition system is highly practical and scalable, consisting purely of
commodity components. The setup consists of a set of displays for con-
trolled illumination for reflectance capture, in conjunction with multi-
view acquisition of facial geometry. We additionally present a novel set
of modulated binary illumination patterns for efficient acquisition of re-
flectance and photometric normals using our setup, with diffuse-specular
separation. We demonstrate high-quality results with two different vari-
ants of the capture setup – one entirely consisting of portable mobile
devices targeting static facial capture, and the other consisting of desk-
top LCD displays targeting both static and dynamic facial capture.
facial capture including geometry and facial appearance. The proposed
acquisition system is highly practical and scalable, consisting purely of
commodity components. The setup consists of a set of displays for con-
trolled illumination for reflectance capture, in conjunction with multi-
view acquisition of facial geometry. We additionally present a novel set
of modulated binary illumination patterns for efficient acquisition of re-
flectance and photometric normals using our setup, with diffuse-specular
separation. We demonstrate high-quality results with two different vari-
ants of the capture setup – one entirely consisting of portable mobile
devices targeting static facial capture, and the other consisting of desk-
top LCD displays targeting both static and dynamic facial capture.
Date Issued
2022-11-11
Date Acceptance
2022-07-08
Citation
Lecture Notes in Computer Science, 2022, 13666, pp.522-537
ISBN
978-3-031-20067-0
ISSN
0302-9743
Publisher
Springer
Start Page
522
End Page
537
Journal / Book Title
Lecture Notes in Computer Science
Volume
13666
Copyright Statement
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG. The final publication is available at Springer via https://link.springer.com/chapter/10.1007/978-3-031-20068-7_30
Identifier
https://doi.org/10.1007/978-3-031-20068-7_30
Source
European Conference on Computer Vision (ECCV) 2022
Subjects
Artificial Intelligence & Image Processing
Publication Status
Published online
Start Date
2022-10-23
Finish Date
2022-10-27
Coverage Spatial
Tel Aviv, Israel
Date Publish Online
2022-11-11