Peng Weilong, Su Yong, Tang Keke, Xu Chao, Feng Zhiyong, Fang Meie
School of Computer Science and Cyber Engineering, Guangzhou University, Guangzhou, China.
Tianjin Key Laboratory of Wireless Mobile Communications and Power Transmission, Tianjin Normal University, Tianjin, China.
Front Neurorobot. 2021 Apr 13;15:652562. doi: 10.3389/fnbot.2021.652562. eCollection 2021.
A number of methods have been proposed for face reconstruction from single/multiple image(s). However, it is still a challenge to do reconstruction for limited number of wild images, in which there exists complex different imaging conditions, various face appearance, and limited number of high-quality images. And most current mesh model based methods cannot generate high-quality face model because of the local mapping deviation in geometric optics and distortion error brought by discrete differential operation. In this paper, accurate geometrical consistency modeling on B-spline parameter domain is proposed to reconstruct high-quality face surface from the various images. The modeling is completely consistent with the law of geometric optics, and B-spline reduces the distortion during surface deformation. In our method, 0th- and 1st-order consistency of stereo are formulated based on low-rank texture structures and local normals, respectively, to approach the pinpoint geometric modeling for face reconstruction. A practical solution combining the two consistency as well as an iterative algorithm is proposed to optimize high-detailed B-spline face effectively. Extensive empirical evaluations on synthetic data and unconstrained data are conducted, and the experimental results demonstrate the effectiveness of our method on challenging scenario, e.g., limited number of images with different head poses, illuminations, and expressions.
已经提出了许多从单张/多张图像进行面部重建的方法。然而，对于有限数量的野生图像进行重建仍然是一个挑战，其中存在复杂多样的成像条件、各种各样的面部外观以及有限数量的高质量图像。而且，由于几何光学中的局部映射偏差以及离散微分运算带来的失真误差，当前大多数基于网格模型的方法无法生成高质量的面部模型。在本文中，提出了在B样条参数域上进行精确的几何一致性建模，以便从各种图像重建高质量的面部表面。该建模与几何光学定律完全一致，并且B样条减少了表面变形期间的失真。在我们的方法中，分别基于低秩纹理结构和局部法线来制定立体视觉的零阶和一阶一致性，以实现用于面部重建的精确几何建模。提出了一种结合这两种一致性的实用解决方案以及一种迭代算法，以有效地优化高细节的B样条面部。对合成数据和无约束数据进行了广泛的实证评估，实验结果证明了我们的方法在具有挑战性的场景中的有效性，例如具有不同头部姿势、光照和表情的有限数量图像。
