基于压缩感知理论的3维人脸快速重建

形变模型是当前人脸重建研究中的一种主要方法。针对形变模型方法中模型构建的缺陷，提出一种基于压缩感知理论的快速三维人脸重建方法。首先，利用压缩感知理论估计三维原型人脸与目标人脸的形状相似性，根据相似性对原型样本进行筛选并构建相应的形变模型，提高建模精度和效率；然后，利用特征点信息进行稀疏模型匹配，并结合径向基函数插值重建生成特定的三维人脸，提高重建表面的平滑性。在BJUT三维数据库和CAS_PEAL二维数据库上的实验结果表明，与经典方法相比，本文方法能够有效地提高重建精度和速度，重建人脸具有较强真实感。

Fast 3D face reconstruction based on compressed sensing

Morphable model based methods have drawn wide attention in 3D face reconstruction community in recent years. To deal with the modeling limitation in traditional morphable models, this paper presents a compressed sensing based method for 3D face reconstruction. In the proposed framework, compressed sensing is firstly used to estimate the similarity between testing and prototype face samples, and a modified morphable model is then built on the selected prototype samples with larger similarity, which can effectively improve the modeling precision and efficiency. Secondly, the model is registered to a testing face image by using facial salient points. Finally, combining the shape recovered by the modified model and the shape obtained by RBFs interpolation, the testing shape is reconstructed with high smoothness. Experiments on BJTU-3D face database and CAS_PEAL 2D face database show that the proposed method outperforms the traditional methods in both reconstruction accuracy and computation complexity. Moreover, its recovered 3D faces achieve higher realistic impression.