Rendering refraction and reflection of eyeglasses for synthetic eye tracker images
This work addresses the need for synthetic eye images with eyeglasses effects for eye tracking algorithm development and evaluation, but it is incremental as it extends existing synthetic image generation methods.
The paper tackled the problem of generating synthetic eye images with realistic eyeglasses effects by simulating refraction and reflection, enabling testing of pupil and glint detection algorithms and gaze estimation routines under various conditions. The result showed that polynomial function fitting calibration performed equally well with and without eyeglasses, while a geometrical eye model's behavior was analyzed when exposed to glasses.
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.