光学学报, 2020, 40 (4): 0410001, 网络出版: 2020-02-11   

基于梯度光图像的高精度三维人脸重建算法 下载: 2372次

High Precision Three-Dimensional Face Reconstruction Algorithm Based on Gradient Light Image
黄硕 1,2,3胡勇 1,2,*巩彩兰 1,2卜弘毅 1,4顾耕 4许琦 4王薇 4
作者单位
1 中国科学院上海技术物理研究所, 上海 200083
2 中国科学院上海技术物理研究所红外探测与成像技术重点实验室, 上海 200083
3 中国科学院大学, 北京 100049
4 中国科学院嘉兴光电工程中心, 浙江 嘉兴 314022
摘要
针对人的脸部特征复杂、细节纹理丰富,获取高精度人脸三维模型成本高、工作量大的问题,提出基于梯度光图像的高精度三维人脸重建算法。利用球形灯光装置建立6种不同的光照模式,并利用偏振光特性对镜面反射光和漫反射光进行分离;利用单向梯度光图像,并基于双向反射分布函数(BRDF)得到反射光方向与法线方向的关系,通过计算获取镜面反射和漫反射法线图;将增强后的镜面反射和漫反射法线图进行融合,并映射到低精度模型上,可以重建出高精度的三维人脸模型。实验结果表明,本文方法计算复杂度低,重建精度高,窗口大小为7×7的高通滤波增强的镜面反射图和漫反射法线图以2∶1的比例融合之后,重建的效果最佳,模型能精细到微尺度级。
Abstract
To address the problems of complex and rich details of face features and heavy work and high cost of reconstructing high-precision three-dimensional (3D) face models, a high-precision 3D face reconstruction algorithm based on the gradient light image is proposed. Six different illumination modes are established using a spherical light device, and specular and diffuse reflection lights are separated using the polarization characteristic. Using a unidirectional gradient light image, specular and diffuse normal maps are obtained by calculation based on relationship between the reflection and normal directions by employing the bidirectional reflectance distribution function (BRDF). The obtained maps are merged and mapped to the low-precision mode to reconstruct a high-precision 3D face model. The experimental results show that the proposed method has low computational complexity and high reconstruction accuracy. Based on the obtained results, it is best to use the high-pass filtering with a window size of 7×7 enhanced specular and diffuse reflection normal maps to achieve the best reconstruction at 2∶1 map ratio fusion. The proposed model can be refined to microscale.

黄硕, 胡勇, 巩彩兰, 卜弘毅, 顾耕, 许琦, 王薇. 基于梯度光图像的高精度三维人脸重建算法[J]. 光学学报, 2020, 40(4): 0410001. Shuo Huang, Yong Hu, Cailan Gong, Hongyi Bo, Geng Gu, Qi Xu, Wei Wang. High Precision Three-Dimensional Face Reconstruction Algorithm Based on Gradient Light Image[J]. Acta Optica Sinica, 2020, 40(4): 0410001.

本文已被 6 篇论文引用
被引统计数据来源于中国光学期刊网
引用该论文: TXT   |   EndNote

相关论文

加载中...

关于本站 Cookie 的使用提示

中国光学期刊网使用基于 cookie 的技术来更好地为您提供各项服务,点击此处了解我们的隐私策略。 如您需继续使用本网站,请您授权我们使用本地 cookie 来保存部分信息。
全站搜索
您最值得信赖的光电行业旗舰网络服务平台!