We present a novel system for real-time tracking of facial expressions using egocentric views captured from a set of infrared cameras embedded in a virtual reality (VR) headset. Our technology facilitates any user to accurately drive the facial expressions of virtual characters in a non-intrusive manner and without the need of a lengthy calibration step. At the core of our system is a distillation based approach to train a machine learning model on heterogeneous data and labels coming form multiple sources, \eg synthetic and real images. As part of our dataset, we collected 18k diverse subjects using a lightweight capture setup consisting of a mobile phone and a custom VR headset with extra cameras. To process this data, we developed a robust differentiable rendering pipeline enabling us to automatically extract facial expression labels. Our system opens up new avenues for communication and expression in virtual environments, with applications in video conferencing, gaming, entertainment, and remote collaboration.
@article{arxiv.2601.03507,
title = {REFA: Real-time Egocentric Facial Animations for Virtual Reality},
author = {Qiang Zhang and Tong Xiao and Haroun Habeeb and Larissa Laich and Sofien Bouaziz and Patrick Snape and Wenjing Zhang and Matthew Cioffi and Peizhao Zhang and Pavel Pidlypenskyi and Winnie Lin and Luming Ma and Mengjiao Wang and Kunpeng Li and Chengjiang Long and Steven Song and Martin Prazak and Alexander Sjoholm and Ajinkya Deogade and Jaebong Lee and Julio Delgado Mangas and Amaury Aubel},
journal= {arXiv preprint arXiv:2601.03507},
year = {2026}
}