We present BlazeFace, a lightweight and well-performing face detector tailored for mobile GPU inference. It runs at a speed of 200-1000+ FPS on flagship devices. This super-realtime performance enables it to be applied to any augmented reality pipeline that requires an accurate facial region of interest as an input for task-specific models, such as 2D/3D facial keypoint or geometry estimation, facial features or expression classification, and face region segmentation. Our contributions include a lightweight feature extraction network inspired by, but distinct from MobileNetV1/V2, a GPU-friendly anchor scheme modified from Single Shot MultiBox Detector (SSD), and an improved tie resolution strategy alternative to non-maximum suppression.
Cite
@article{arxiv.1907.05047,
title = {BlazeFace: Sub-millisecond Neural Face Detection on Mobile GPUs},
author = {Valentin Bazarevsky and Yury Kartynnik and Andrey Vakunov and Karthik Raveendran and Matthias Grundmann},
journal= {arXiv preprint arXiv:1907.05047},
year = {2019}
}
Comments
4 pages, 3 figures; CVPR Workshop on Computer Vision for Augmented and Virtual Reality, Long Beach, CA, USA, 2019