Non-contact physiological measurement has the potential to provide low-cost, non-invasive health monitoring. However, machine vision approaches are often limited by the availability and diversity of annotated video datasets resulting in poor generalization to complex real-life conditions. To address these challenges, this work proposes the use of synthetic avatars that display facial blood flow changes and allow for systematic generation of samples under a wide variety of conditions. Our results show that training on both simulated and real video data can lead to performance gains under challenging conditions. We show state-of-the-art performance on three large benchmark datasets and improved robustness to skin type and motion.
@article{arxiv.2010.12949,
title = {Advancing Non-Contact Vital Sign Measurement using Synthetic Avatars},
author = {Daniel McDuff and Javier Hernandez and Erroll Wood and Xin Liu and Tadas Baltrusaitis},
journal= {arXiv preprint arXiv:2010.12949},
year = {2020}
}