论文标题
注意网格：实时的高保真面孔网格预测
Attention Mesh: High-fidelity Face Mesh Prediction in Real-time
论文作者
论文摘要
我们提出了注意网格，这是一种用于3D面网格预测的轻量级架构，该预测利用了对语义有意义的区域的关注。我们的神经网络是为实时推论而设计的，并在Pixel 2手机上以超过50 fps的速度运行。我们的解决方案启用了诸如AR化妆，眼动追踪和AR伪造等应用，这些应用依赖于眼睛和嘴唇区域的高度准确地标。我们的主要贡献是一个统一的网络体系结构，在面部地标上与多阶段级联方法相同的精度具有相同的准确性，同时又快30％。
We present Attention Mesh, a lightweight architecture for 3D face mesh prediction that uses attention to semantically meaningful regions. Our neural network is designed for real-time on-device inference and runs at over 50 FPS on a Pixel 2 phone. Our solution enables applications like AR makeup, eye tracking and AR puppeteering that rely on highly accurate landmarks for eye and lips regions. Our main contribution is a unified network architecture that achieves the same accuracy on facial landmarks as a multi-stage cascaded approach, while being 30 percent faster.
