How to accurately reconstruct the 3D model human face is a challenge issue in the computer vision. Due to the complexity of face reconstruction and diversity of face features, most existing methods are aimed at reconstructing a smooth face model with ignoring face details. In this paper a novel deep learning-based face reconstruction method is proposed. It contains two modules: initial face reconstruction and face details synthesis. In the initial face reconstruction module, a neural network is used to detect the facial feature points and the angle of the pose face, and 3D Morphable Model (3DMM) is used to reconstruct the rough shape of the face model. In the face detail synthesis module, Conditional Generation Adversarial Network (CGAN) is used to synthesize the displacement map. The map provides texture features to render to the face surface reconstruction, so as to reflect the face details. Our proposal is evaluated by Facescape dataset in experiments and achieved better performance than other current methods.

中文翻译：

---

基于3DMM和位移图的细节3D人脸重建

如何准确地重建3D模型人脸是计算机视觉中的一个挑战问题。由于人脸重建的复杂性和人脸特征的多样性，现有的大多数方法都旨在重建一个忽略人脸细节的平滑人脸模型。在本文中，提出了一种新的基于深度学习的人脸重建方法。它包含两个模块：初始人脸重建和人脸细节合成。在初始人脸重建模块中，使用神经网络检测人脸特征点和姿势人脸的角度，并使用3D Morphable Model（3DMM）重建人脸模型的粗略形状。在人脸细节合成模块中，使用条件生成对抗网络（CGAN）合成置换图。地图提供纹理特征来渲染到人脸表面重建，从而反映人脸细节。我们的提议在实验中由 Facescape 数据集进行评估，并取得了比其他当前方法更好的性能。