Rendering refraction and reflection of eyeglasses for synthetic eye tracker images

TL;DR

This paper introduces a method to generate synthetic eye images with realistic refraction and reflection effects of eyeglasses, aiding in the development and evaluation of gaze estimation algorithms.

Contribution

It extends synthetic eye image generation by modeling eyeglasses effects, enabling better testing of gaze estimation and detection algorithms under various conditions.

Findings

Polynomial calibration performs consistently with and without eyeglasses.

Geometrical eye models are affected by eyeglasses in gaze estimation.

Synthetic images help evaluate detection algorithms under different reflections.

Abstract

While for the evaluation of robustness of eye tracking algorithms the use of real-world data is essential, there are many applications where simulated, synthetic eye images are of advantage. They can generate labelled ground-truth data for appearance based gaze estimation algorithms or enable the development of model based gaze estimation techniques by showing the influence on gaze estimation error of different model factors that can then be simplified or extended. We extend the generation of synthetic eye images by a simulation of refraction and reflection for eyeglasses. On the one hand this allows for the testing of pupil and glint detection algorithms under different illumination and reflection conditions, on the other hand the error of gaze estimation routines can be estimated in conjunction with different eyeglasses. We show how a polynomial function fitting calibration performs equally well with and without eyeglasses, and how a geometrical eye model behaves when exposed to glasses.