A Statistical Approach to Continuous Self-Calibrating Eye Gaze Tracking for Head-Mounted Virtual Reality Systems

TL;DR

This paper introduces a continuous, automatic eye gaze tracking method for VR headsets that eliminates explicit calibration and adapts to headset movements using Gaussian Process Regression models.

Contribution

It proposes a novel, self-calibrating eye tracking algorithm inspired by smooth pursuit eye motion, improving convenience and accuracy in VR systems.

Findings

Achieves near-calibration accuracy without explicit calibration.

Automatically compensates for headset movements.

Uses Gaussian Process Regression for continuous mapping.

Abstract

We present a novel, automatic eye gaze tracking scheme inspired by smooth pursuit eye motion while playing mobile games or watching virtual reality contents. Our algorithm continuously calibrates an eye tracking system for a head mounted display. This eliminates the need for an explicit calibration step and automatically compensates for small movements of the headset with respect to the head. The algorithm finds correspondences between corneal motion and screen space motion, and uses these to generate Gaussian Process Regression models. A combination of those models provides a continuous mapping from corneal position to screen space position. Accuracy is nearly as good as achieved with an explicit calibration step.