从2D帧到3D人脸建模的基于Candide模型的合成方法

An way of synthesizing 3D Face from 2D Frame Based on Candide Model

本文应用Candide模型作为通用的3D人脸模型,介绍了一种结合自动和交互方式的合成方法,从2D视频帧合成3D人脸模型。首先利用可变形模板自动提取脸部的特征点,在图像质量不好时,可以进行交互式操作。然后对通用模型进行全局变换和局部变换,对于非特征点的调整,采用径向基函数进行插值。最后通过对图像划分区域,分段完成纹理贴图,合成3D人脸模型。

To build 3D face model from 2D video frame, the paper introduces a synthesis method of combining automation and interaction mode, using Candide face model as the generic model. First eigenpoints are extracted by deformable templates, which can be replaced by manual manipulation when the image＇ s quality is bad. Second the model is adapted globally and locally and the noneigenpoints is interpolated by RBF. Finally texture mapping is completed according to different regions on the face and thus the 3D face model is synthesized.