Lab eye-tracking data converted for better VR authentication
Measurement-Guided Conversion of Laboratory Eye-Tracking Data for VR Authentication
Human-Computer Interaction
Summary
Eye movement can be used to unlock virtual reality (VR) devices, but training this technology needs lots of data taken inside VR, which is hard to get. The authors found a way to change eye-tracking data collected in a lab to look like it was recorded by a VR headset. Their method keeps the important eye movement details while adding the right amount of VR-like noise and errors. This lets systems learn to recognize users in VR more accurately without needing much real VR data.
What this means in practice
- •For vr developers: Create VR authentication systems using converted lab eye-tracking data without needing extensive VR-specific training data.
- •For biometric security teams: Improve user verification methods by training authenticators on realistically converted eye movement data for VR environments.
Authors
Md Arif Shahriar, Mehedi Hasan Raju, Oleg V. Komogortsev
Abstract
Eye-movement authentication in virtual reality (VR) needs longitudinal training data, yet most such datasets come from lab trackers. We convert lab recordings to a VR headset's signal quality while keeping their eye movement, using only unpaired VR recordings of other people. Measurements show that the headset's added noise dominates above 7.8 Hz and that its quality is consistent within a person. A parametric device model re-creates the headset's sampling, a person-consistent calibration error and spectrally shaped noise, and a frequency-locked diffusion renderer re-textures that high-frequency noise. Converted GazeBase recordings match GazeBaseVR in noise level and accuracy, keep their source's saccade dynamics, and are harder to tell from real VR data than two prior conversions. An authenticator trained only on converted data verifies unseen VR users at a 5.9% equal error rate with 45 s of gaze, close to real VR training (5.8%); with 5 s, a gap remains.