Eyemotion: Classifying facial expressions in VR using eye-tracking cameras

TL;DR

This paper introduces Eyemotion, an eye-tracking based algorithm that infers facial expressions in VR to enhance social interaction, achieving high accuracy without external cameras.

Contribution

It presents a novel eye-tracking approach for facial expression recognition in VR, including a new data collection pipeline and personalization method for CNNs.

Findings

Achieved 74% accuracy on 5 emotive expressions

Achieved 70% accuracy on 10 facial action units

Outperformed human raters in expression recognition

Abstract

One of the main challenges of social interaction in virtual reality settings is that head-mounted displays occlude a large portion of the face, blocking facial expressions and thereby restricting social engagement cues among users. Hence, auxiliary means of sensing and conveying these expressions are needed. We present an algorithm to automatically infer expressions by analyzing only a partially occluded face while the user is engaged in a virtual reality experience. Specifically, we show that images of the user's eyes captured from an IR gaze-tracking camera within a VR headset are sufficient to infer a select subset of facial expressions without the use of any fixed external camera. Using these inferences, we can generate dynamic avatars in real-time which function as an expressive surrogate for the user. We propose a novel data collection pipeline as well as a novel approach for increasing CNN accuracy via personalization. Our results show a mean accuracy of 74% ($F1$ of 0.73) among 5 `emotive' expressions and a mean accuracy of 70% ($F1$ of 0.68) among 10 distinct facial action units, outperforming human raters.