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.

本文提出了一种利用紧凑、快速的 CNN 模型在移动设备上实现实时重构的方法，通过使用传统的形态模型自动注释大量图像以供 CNN 训练，并优化 MobileNet CNNs 模型以改进速度、模型大小和保持最先进的重构精度。

MobileFace：高效 CNN 回归的 3D 人脸重建

MobileFace: 3D Face Reconstruction with Efficient CNN Regression

Fast and robust three-dimensional reconstruction of facial geometric
structure from a single image is a challenging task with numerous applications.
Here, we introduce a learning-based approach for reconstructing a
three-dimensional face from a single image. Recent face recovery methods rely
on accurate localization of key characteristic points. In contrast, the
proposed approach is based on a Convolutional-Neural-Network (CNN) which
extracts the face geometry directly from its image. Although such deep
architectures outperform other models in complex computer vision problems,
training them properly requires a large dataset of annotated examples. In the
case of three-dimensional faces, currently, there are no large volume data
sets, while acquiring such big-data is a tedious task. As an alternative, we
propose to generate random, yet nearly photo-realistic, facial images for which
the geometric form is known. The suggested model successfully recovers facial
shapes from real images, even for faces with extreme expressions and under
various lighting conditions.

本论文介绍了一种基于卷积神经网络和生成随机几乎逼真的面部图像的方法，可以通过单张照片快速、稳健地重建面部的三维几何结构，即使在极端表情和各种光照条件下也可以成功恢复面部形状。