真实感3D人脸快速建模研究

Rapid 3D modeling of personalized face

现有的三维人脸建模方法存在三点不足:建模条件苛刻、建模精度不高和建模时间长。针对以上不足,提出明暗恢复形状(SFS)和局部形变模型融合的3D人脸建模方法。该方法利用SFS快速恢复3D人脸粗糙数据,得到3D轮廓脸;然后分别对人脸不同局部应用形变模型恢复其局部3D精确数据,并使用其对轮廓脸进行内插平滑处理重建出高精度3D人脸模型。实验结果表明:该方法能够获得较好的建模精度,在短时间内可以通过单幅真实图像重建出个性化的三维人脸模型。

The existing 3D face modeling methods have three disadvantages. Firstly, it needs very high modeling conditions; secondly, the lower modeling accuracy ; thirdly, the long modeling time. To address this problem, proposed an algorithm integra- tion of shape-from-shading （SFS） and local morphable model. This method rapidly obtained 3D face rough data （which called 3D face profile） by SFS firstly. Then, local 3D accurated data recovery by establishing local morphable model, and reconstruc- tion of a high-precision 3D face model by carried out interpolation smoothing on the 3D face profile with local 3D accurate data. Experimental results show that this method can obtain better modeling precision, and can reconstruction of personalized 3D face model from a single real-world photo in a short time.