Department of Electrical and Electronics Engineering, Yonsei University, 134 Shinchon-dong, Seodaemun-gu, Seoul 120-749, Korea.
Sensors (Basel). 2012 Sep 25;12(10):12870-89. doi: 10.3390/s121012870.
In this paper, we focus on the problem of the accuracy performance of 3D face modeling techniques using corresponding features in multiple views, which is quite sensitive to feature extraction errors. To solve the problem, we adopt a statistical model-based 3D face modeling approach in a mirror system consisting of two mirrors and a camera. The overall procedure of our 3D facial modeling method has two primary steps: 3D facial shape estimation using a multiple 3D face deformable model and texture mapping using seamless cloning that is a type of gradient-domain blending. To evaluate our method's performance, we generate 3D faces of 30 individuals and then carry out two tests: accuracy test and robustness test. Our method shows not only highly accurate 3D face shape results when compared with the ground truth, but also robustness to feature extraction errors. Moreover, 3D face rendering results intuitively show that our method is more robust to feature extraction errors than other 3D face modeling methods. An additional contribution of our method is that a wide range of face textures can be acquired by the mirror system. By using this texture map, we generate realistic 3D face for individuals at the end of the paper.
在本文中，我们专注于使用多视图中的对应特征进行 3D 人脸建模技术的准确性性能问题，该问题对特征提取错误非常敏感。为了解决这个问题，我们在由两个镜子和一个相机组成的镜像系统中采用基于统计模型的 3D 人脸建模方法。我们的 3D 面部建模方法的总体过程有两个主要步骤：使用多个 3D 人脸可变形模型进行 3D 人脸形状估计和使用无缝克隆（一种梯度域混合类型）进行纹理映射。为了评估我们方法的性能，我们生成了 30 个人的 3D 人脸，然后进行了两项测试：准确性测试和鲁棒性测试。与真实值相比，我们的方法不仅具有高度准确的 3D 人脸形状结果，而且对特征提取错误具有鲁棒性。此外，3D 人脸渲染结果直观地表明，我们的方法比其他 3D 人脸建模方法更能抵抗特征提取错误。我们方法的另一个贡献是，镜像系统可以获取广泛的人脸纹理。通过使用这种纹理图，我们在论文的最后为个人生成逼真的 3D 人脸。
