LEyes: A Lightweight Framework for Deep Learning-Based Eye Tracking using Synthetic Eye Images
This addresses the problem of dataset scarcity and generalizability for researchers and developers in eye tracking, though it is incremental as it builds on existing synthetic data methods.
The paper tackles the problem of inadequate training datasets for deep learning-based gaze estimation by introducing LEyes, a lightweight framework that generates synthetic eye images using simple light distributions instead of photorealistic methods. The result is that models trained with LEyes perform on-par or better than state-of-the-art algorithms in pupil and CR localization and outperform industry standard eye trackers with more cost-effective hardware.
Deep learning has bolstered gaze estimation techniques, but real-world deployment has been impeded by inadequate training datasets. This problem is exacerbated by both hardware-induced variations in eye images and inherent biological differences across the recorded participants, leading to both feature and pixel-level variance that hinders the generalizability of models trained on specific datasets. While synthetic datasets can be a solution, their creation is both time and resource-intensive. To address this problem, we present a framework called Light Eyes or "LEyes" which, unlike conventional photorealistic methods, only models key image features required for video-based eye tracking using simple light distributions. LEyes facilitates easy configuration for training neural networks across diverse gaze-estimation tasks. We demonstrate that models trained using LEyes are consistently on-par or outperform other state-of-the-art algorithms in terms of pupil and CR localization across well-known datasets. In addition, a LEyes trained model outperforms the industry standard eye tracker using significantly more cost-effective hardware. Going forward, we are confident that LEyes will revolutionize synthetic data generation for gaze estimation models, and lead to significant improvements of the next generation video-based eye trackers.