面向形变模型的三维人脸建模研究及其改进  

3D Face Reconstruction of Morphable Model and Its Improvement

作　　者：廖海斌[1] 陈庆虎[1] 鄢煜尘[1] 

机构地区：[1]武汉大学电子信息学院,武汉市珞喻路129号430079

出　　处：《武汉大学学报（信息科学版）》2011年第2期176-180,共5页Geomatics and Information Science of Wuhan University

基　　金：中央高校基本科研业务费专项基金资助项目(20102120103000004);河南省科技攻关基金资助项目(092102210398)

摘　　要：针对传统三维形变模型效率低的不足,提出了一种简洁高效的三维形变模型进行个性化三维人脸重建。首先建立基于关键特征区域重采样的标准三维人脸数据库,实现三维人脸的稠密对应;然后选择与目标人脸奇异值向量最相似的人脸作为形变模型的基空间,进行形变模型成分的动态选择;最后引入基于特征点的稀疏形变模型替代原稠密对应形变模型进行匹配求解线性组合系数,并完成特定的三维人脸重建。实验结果表明,本文方法建模时间短、复杂度低,通过单张图片的少量特征点能生成逼真的三维人脸模型。A simple and efficient linear 3D deformable model is proposed to reconstruct individuation 3D human face.First,a standardized 3D face database based on resampling of key feature region is built to realize the dense correspondence among faces.Then,the faces of which singular value vector is most similar to the target face are selected as the basic space to choose components of morphable model dynamically.Finally,the original morphable model is replaced to a feature-point based sparse morphable model to reduce the difficulty of solving linear combination coefficients.The experimental results show that this method has the short modeling time and low complexity,and can generate a realistic 3D faces from a few landmarks of real-world photos.

关 键 词：人脸建模 形变模型 稠密对应 奇异值分解 

分 类 号：P237.3[天文地球—摄影测量与遥感]