摘要
用二维人脸照片构造三维特定人脸模型是三维人脸建模研究的热点问题。采用立体视觉重建三维特征点,通过人脸正侧面照片特征点的分层、分部位的径向基函数重构一般人脸模型,得到部位轮廓特征明显的三维特定人脸模型,利用B样条曲线进行三维人脸曲面重构;然后运用拉普拉斯金字塔法得到近似的人脸全视角纹理图;再将近似人脸全视角纹理图映射到三维特定人脸模型,从而得到三维特定真实感的人脸模型。实验结果表明,该方法计算简单,生成特定人脸模型效果逼真,可用于特定人脸动画制作的逼真人脸建模。
3-D specific face model construction by way of 2-D face image is an active topic in 3-D face modeling research. Stereoscopic sense of vision is used to reconstruct 3-D feature points. Then multi-layer and multi-region RBF (radial basis function) based on feature points of frontal and profile face image is adopted for reconstructing the generic face model to get 3-D specific face model with visible organ characters. Moreover, B spline is used in 3-D face curve reconstruction. Then the near face global texture is mapped onto the reconstructed specific face model and the 3-D realistic specific human face model is obtained. Experiments show that the method is easy for constructing near face global texture, in which the reconstructed specific face model is natural and realistic, and is used for realistic specific face modeling in facial animation.
出处
《计算机工程与设计》
CSCD
北大核心
2008年第17期4511-4514,共4页
Computer Engineering and Design
基金
广东省自然科学基金项目(07010869
032356)
广东省江门市科技攻关基金项目(江财企[2006]59号)
关键词
立体视觉
径向基函数
B样条曲线
人脸重构
特征提取
stereoscopic sense of vision
B spline
RBFs
face reconstruction
feature extraction