由粗到精的三维人脸稀疏重建方法

针对传统三维人脸重建算法精度不高的问题, 提出一种由粗到精的三维人脸稀疏重建方法。根据稀疏形变模型方法对待重建人脸的部分区域显著点进行重建, 得到第1步重建结果, 并在此基础上进行后续重建。将第1步的重建结果作为新的参考模型, 求取待重建人脸与参考模型的特征点的坐标投影距离, 从而求取参考模型的形变因子, 完成最终三维人脸的重建。由于两步稀疏重建的作用不同, 对重建过程中参数的选取也采用不同方式。实验结果表明, 该方法能有效提高人脸重建精度, 同时保持较快的重建速度。

Coarse-to-Fine 3D Face Reconstruction Method from Partial Information

To improve the accuracy of 3D face reconstruction, a novel coarse-to-fine 3D reconstruction method is proposed. With salient points in each region, a rough shape is reconstructed based on SRSD (Surface Reconstruction from SparseData) method. Since the shape reconstructed is a rough approximation ofreal model, the following reconstruction based on this shape is more accurate. Taking the rough shape as reference model, distance of feature points between 2D face and the projection of reference model can be calculated. Then deforming factors are computed and the final precise shape is reconstructed. Since the roles of each reconstruction step are different, parameters in each step are selected in different ways. Experimental results show that this method can effectively improve the accuracy while having similar computation speed.