Face Normals “in-the-wild” using Fully Convolutional Networks[cvpr2017 Face Normals] 李培
Contributions:
- Exploit the currently available facial databases for dataset construction and tailor a deep convolutional neural network to the task of estimating facial surface normals ‘in-the-wild’
主要論述了使用300W的數據集來訓練生成一個3DMM參數化模型,大部分都在講通過已有的數據集來生成用于訓練的數據。
Pipeline:
pipeline
Result:
result