Abstract

This paper proposes a high accuracy 3D face model reconstruction method which is based on machine learning algorithm. The framework contains a features auto-encoder and a Generative-Adversarial Network. We use more than 20,000 high quality 3D face medal to train this network.

© 2018 The Author(s)

PDF Article
This paper was not presented at the conference

More Like This
2D+3D Face Imaging for Stand-off Biometric Identification

Brian Redman, John Novotny, Taylor Grow, Van Rudd, Nathan Woody, Michael Hinckley, Paul McCumber, Nathan Rogers, Michael Hoening, Kelli Kubala, Scott Shald, Radek Uberna, Tiffanie D’Alberto, Thomas Höft, Russell Sibell, and Frederick W. Wheeler
ATuF4 CLEO: Applications and Technology (CLEO_AT) 2011

Analysis of 3D Image Reconstruction for Spherical Object Using Convolutional Neural Network in Digital Holography

Wooyoung Jeong, Kyungchan Son, Wonseok Jeon, and Hyunseok Yang
JTu4A.24 3D Image Acquisition and Display: Technology, Perception and Applications (3D) 2018

High Resolution Single-Shot 3D Imaging with the “3D movie camera”

Florian Willomitzer and Gerd Häusler
3M3G.2 3D Image Acquisition and Display: Technology, Perception and Applications (3D) 2018

References

You do not have subscription access to this journal. Citation lists with outbound citation links are available to subscribers only. You may subscribe either as an OSA member, or as an authorized user of your institution.

Contact your librarian or system administrator
or
Login to access OSA Member Subscription