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： 2381次
High Precision Three-Dimensional Face Reconstruction Algorithm Based on Gradient Light Image
图 & 表
图 2. 反射光分离结果。(a)垂直极化图像;(b)平行极化图像;(c)镜面反射光图像
Fig. 2. Results of reflected light separation. (a) Vertically polarized image; (b) parallel polarized image; (c) specular reflection image
图 3. 不同方向的梯度光图像。(a)沿X方向;(b)沿-X方向;(c)沿Y方向;(d)沿-Y方向;(e)沿Z方向;(f)全亮光
Fig. 3. Gradient light images in different directions. (a) Along the X direction; (b) along the -X direction; (c) along the Y direction; (d) along the -Y direction; (e) along the Z direction; (f) all light
图 5. 图像获取装置。(a)拍摄装置; (b)拍摄相机的相对位置
Fig. 5. Image acquisition device. (a) Shooting device; (b) relative position of the cameras
图 6. 镜面反射和漫反射分离实验
Fig. 6. Experiment of specular reflection and diffuse reflection separation
图 7. 法线融合效果图。(a)漫反射法线图;(b)镜面反射法线图; (c)融合后法线图
Fig. 7. Results of normal map fusion. (a) Diffuse reflection normal map; (b) specular reflection normal map; (c) fusion normal map
图 8. 不同融合方式的法线图重建效果对比。(a)低精度模型;(b)按照2∶1融合重建;(c) 5×5高通滤波和1∶1融合比例重建;(d) 5×5高通滤波和2∶1融合比例重建;(e) 7×7高通滤波和1∶1融合比例重建;(f) 7×7高通滤波和2∶1的融合比例重建
Fig. 8. Comparison of normal map reconstruction with different fusion modes. (a) Low precision model; (b) reconstruction with 2∶1 fusion ratio; (c) reconstruction with 5×5 high-pass filtering and 1∶1 fusion ratio; (d) reconstruction with 5×5 high-pass filtering and 2∶1 fusion ratio; (e) reconstruction with 7×7 high-pass filtering and 1∶1 fusion ratio; (f) reconstruction with 7×7 high-pass filtering and 2∶1 fusion ratio
图 9. 多视角图像。(a)多视角图像;(b)多视角法线图
Fig. 9. Multi-view images. (a) Multi-view images; (b) multi-view normal maps
表 1简化模型参数
Table1. Parameters of simplified model
|
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.
PDF全文
