Polarization-resolved imaging improves eye tracking

TL;DR

This paper introduces polarization-resolved near-infrared imaging for eye tracking, demonstrating improved accuracy and robustness over traditional intensity-based methods using a novel PET system and machine learning.

Contribution

The study presents a polarization-enabled eye tracking system that enhances feature detection and reduces gaze error, advancing wearable eye tracking technology.

Findings

Reduced median 95th-percentile gaze error by 10-16%

Effective in presence of eyelid occlusions and pupil variations

Demonstrated on 346 participants

Abstract

Polarization-resolved near-infrared imaging adds a useful optical contrast mechanism to eye tracking by measuring the polarization state of light reflected by ocular tissues in addition to its intensity. In this paper we demonstrate how this contrast can be used to enable eye tracking. Specifically, we demonstrate that a polarization-enabled eye tracking (PET) system composed of a polarization--filter--array camera paired with a linearly polarized near-infrared illuminator can reveal trackable features across the sclera and gaze-informative patterns on the cornea, largely absent in intensity-only images. Across a cohort of 346 participants, convolutional neural network based machine learning models trained on data from PET reduced the median 95th-percentile absolute gaze error by 10--16\% relative to capacity-matched intensity baselines under nominal conditions and in the presence of eyelid occlusions, eye-relief changes, and pupil-size variation. These results link light--tissue polarization effects to practical gains in human--computer interaction and position PET as a simple, robust sensing modality for future wearable devices.