Skip to main content

Lund University Publications

LUND UNIVERSITY LIBRARIES

LEyes : A lightweight framework for deep learning-based eye tracking using synthetic eye images

Byrne, Sean Anthony ; Maquiling, Virmarie ; Nyström, Marcus LU orcid ; Kasneci, Enkelejda and Niehorster, Diederick C LU orcid (2025) In Behavior Research Methods 57.
Abstract

Deep learning methods have significantly advanced the field of gaze estimation, yet the development of these algorithms is often hindered by a lack of appropriate publicly accessible training datasets. Moreover, models trained on the few available datasets often fail to generalize to new datasets due to both discrepancies in hardware and biological diversity among subjects. To mitigate these challenges, the research community has frequently turned to synthetic datasets, although this approach also has drawbacks, such as the computational resource and labor-intensive nature of creating photorealistic representations of eye images to be used as training data. In response, we introduce "Light Eyes" (LEyes), a novel framework that diverges... (More)

Deep learning methods have significantly advanced the field of gaze estimation, yet the development of these algorithms is often hindered by a lack of appropriate publicly accessible training datasets. Moreover, models trained on the few available datasets often fail to generalize to new datasets due to both discrepancies in hardware and biological diversity among subjects. To mitigate these challenges, the research community has frequently turned to synthetic datasets, although this approach also has drawbacks, such as the computational resource and labor-intensive nature of creating photorealistic representations of eye images to be used as training data. In response, we introduce "Light Eyes" (LEyes), a novel framework that diverges from traditional photorealistic methods by utilizing simple synthetic image generators to train neural networks for detecting key image features like pupils and corneal reflections, diverging from traditional photorealistic approaches. LEyes facilitates the generation of synthetic data on the fly that is adaptable to any recording device and enhances the efficiency of training neural networks for a wide range of gaze-estimation tasks. Presented evaluations show that LEyes, in many cases, outperforms existing methods in accurately identifying and localizing pupils and corneal reflections across diverse datasets. Additionally, models trained using LEyes data outperform standard eye trackers while employing more cost-effective hardware, offering a promising avenue to overcome the current limitations in gaze estimation technology.

(Less)
Please use this url to cite or link to this publication:
author
; ; ; and
organization
publishing date
type
Contribution to journal
publication status
published
subject
keywords
Deep Learning, Humans, Eye-Tracking Technology, Neural Networks, Computer, Algorithms, Eye Movements/physiology, Fixation, Ocular/physiology, Image Processing, Computer-Assisted/methods
in
Behavior Research Methods
volume
57
article number
129
pages
26 pages
publisher
Springer
external identifiers
  • scopus:105001724204
  • pmid:40164925
ISSN
1554-3528
DOI
10.3758/s13428-025-02645-y
language
English
LU publication?
yes
additional info
© 2025. The Author(s).
id
7526b230-e998-4727-b673-09e6c2a83b5b
date added to LUP
2025-04-05 19:36:44
date last changed
2025-07-14 07:56:00
@article{7526b230-e998-4727-b673-09e6c2a83b5b,
  abstract     = {{<p>Deep learning methods have significantly advanced the field of gaze estimation, yet the development of these algorithms is often hindered by a lack of appropriate publicly accessible training datasets. Moreover, models trained on the few available datasets often fail to generalize to new datasets due to both discrepancies in hardware and biological diversity among subjects. To mitigate these challenges, the research community has frequently turned to synthetic datasets, although this approach also has drawbacks, such as the computational resource and labor-intensive nature of creating photorealistic representations of eye images to be used as training data. In response, we introduce "Light Eyes" (LEyes), a novel framework that diverges from traditional photorealistic methods by utilizing simple synthetic image generators to train neural networks for detecting key image features like pupils and corneal reflections, diverging from traditional photorealistic approaches. LEyes facilitates the generation of synthetic data on the fly that is adaptable to any recording device and enhances the efficiency of training neural networks for a wide range of gaze-estimation tasks. Presented evaluations show that LEyes, in many cases, outperforms existing methods in accurately identifying and localizing pupils and corneal reflections across diverse datasets. Additionally, models trained using LEyes data outperform standard eye trackers while employing more cost-effective hardware, offering a promising avenue to overcome the current limitations in gaze estimation technology.</p>}},
  author       = {{Byrne, Sean Anthony and Maquiling, Virmarie and Nyström, Marcus and Kasneci, Enkelejda and Niehorster, Diederick C}},
  issn         = {{1554-3528}},
  keywords     = {{Deep Learning; Humans; Eye-Tracking Technology; Neural Networks, Computer; Algorithms; Eye Movements/physiology; Fixation, Ocular/physiology; Image Processing, Computer-Assisted/methods}},
  language     = {{eng}},
  month        = {{03}},
  publisher    = {{Springer}},
  series       = {{Behavior Research Methods}},
  title        = {{LEyes : A lightweight framework for deep learning-based eye tracking using synthetic eye images}},
  url          = {{http://dx.doi.org/10.3758/s13428-025-02645-y}},
  doi          = {{10.3758/s13428-025-02645-y}},
  volume       = {{57}},
  year         = {{2025}},
}