Attention Mesh: High-fidelity Face Mesh Prediction in Real-time
arXiv:2006.10962
Abstract
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.
4 pages, 5 figures; CVPR Workshop on Computer Vision for Augmented and Virtual Reality, Seattle, WA, USA, 2020