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


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
Login to access OSA Member Subscription