基于特征点的三维人脸形变模型

针对传统三维人脸形变模型效率低的不足,提出了一个基于特征点的线性人脸形变模型.首先,提出一种基于平面模板的对应方法,自动地实现了三维人脸的稠密点对应,建立了人脸线性模型.然后,提出一个基于动态成分的线性形变模型,选择与目标人脸最相关的主成分作为形变模型的基空间.最后,采用一个全局与局部双重形变框架来完成人脸形状建模.实验结果表明,该方法能够获得较好的建模精度,可以通过真实照片上的少量特征点生成逼真的三维人脸模型.

3D Face Deformable Model Based on Feature Points

The traditional 3D deformable model is inefficient in face reconstruction. To address this problem, a linear deformable model is proposed based on facial landmarks. First, a 2D template-based alignment algorithm isdeveloped to process the correspondence between faces automatically, and a facial linear model is built. Then, adynamic component-based deforming model is proposed to select the most correlative components as the basicspace. Finally, the facial shape is reconstructed by a double deformation framework, a combination of the globaldeformation and local modification. Experimental results show that this method outperforms the conventionalmethods in modeling precision, and the 3D faces generated from real-world photos are rather realistic based on afew landmarks.