arXiv Analytics

Sign in

arXiv:1809.08809 [cs.CV]AbstractReferencesReviewsResources

MobileFace: 3D Face Reconstruction with Efficient CNN Regression

Nikolai Chinaev, Alexander Chigorin, Ivan Laptev

Published 2018-09-24Version 1

Estimation of facial shapes plays a central role for face transfer and animation. Accurate 3D face reconstruction, however, often deploys iterative and costly methods preventing real-time applications. In this work we design a compact and fast CNN model enabling real-time face reconstruction on mobile devices. For this purpose, we first study more traditional but slow morphable face models and use them to automatically annotate a large set of images for CNN training. We then investigate a class of efficient MobileNet CNNs and adapt such models for the task of shape regression. Our evaluation on three datasets demonstrates significant improvements in the speed and the size of our model while maintaining state-of-the-art reconstruction accuracy.

Related articles: Most relevant | Search more
arXiv:1609.04387 [cs.CV] (Published 2016-09-14)
3D Face Reconstruction by Learning from Synthetic Data
arXiv:1702.05619 [cs.CV] (Published 2017-02-18)
3D Face Reconstruction with Geometry Details from a Single Image
arXiv:1711.05953 [cs.CV] (Published 2017-11-16)
3D Face Reconstruction from Light Field Images: A Model-free Approach