dorsal/arxiv
View SchemaEyeTheia: A Lightweight and Accessible Eye-Tracking Toolbox
| Authors | Stevenson Pather, Niels Martignène, Arnaud Bugnet, Fouad Boutaleb, Fabien D'Hondt, Deise Santana Maia |
|---|---|
| Categories | |
| ArXiv ID | 2601.06279vv1 |
| URL | https://arxiv.org/abs/2601.06279 |
| License | http://creativecommons.org/licenses/by/4.0/ |
Abstract
We introduce EyeTheia, a lightweight and open deep learning pipeline for webcam-based gaze estimation, designed for browser-based experimental platforms and real-world cognitive and clinical research. EyeTheia enables real-time gaze tracking using only a standard laptop webcam, combining MediaPipe-based landmark extraction with a convolutional neural network inspired by iTracker and optional user-specific fine-tuning. We investigate two complementary strategies: adapting a model pretrained on mobile data and training the same architecture from scratch on a desktop-oriented dataset. Validation results on MPIIFaceGaze show comparable performance between both approaches prior to calibration, while lightweight user-specific fine-tuning consistently reduces gaze prediction error. We further evaluate EyeTheia in a realistic Dot-Probe task and compare it to the commercial webcam-based tracker SeeSo SDK. Results indicate strong agreement in left-right gaze allocation during stimulus presentation, despite higher temporal variability. Overall, EyeTheia provides a transparent and extensible solution for low-cost gaze tracking, suitable for scalable and reproducible experimental and clinical studies. The code, trained models, and experimental materials are publicly available.
{
"annotation_id": "751e93a1-1676-4fff-bcec-c3c58035201b",
"date_created": "2026-02-17T05:53:08.810000Z",
"date_modified": "2026-02-17T05:53:08.810000Z",
"file_hash": "2b22a62de4a386a5e0df7c8b802e270249e1162cdbe8f79197c800c5c1505343",
"private": false,
"record": {
"abstract": "We introduce EyeTheia, a lightweight and open deep learning pipeline for webcam-based gaze estimation, designed for browser-based experimental platforms and real-world cognitive and clinical research. EyeTheia enables real-time gaze tracking using only a standard laptop webcam, combining MediaPipe-based landmark extraction with a convolutional neural network inspired by iTracker and optional user-specific fine-tuning. We investigate two complementary strategies: adapting a model pretrained on mobile data and training the same architecture from scratch on a desktop-oriented dataset. Validation results on MPIIFaceGaze show comparable performance between both approaches prior to calibration, while lightweight user-specific fine-tuning consistently reduces gaze prediction error. We further evaluate EyeTheia in a realistic Dot-Probe task and compare it to the commercial webcam-based tracker SeeSo SDK. Results indicate strong agreement in left-right gaze allocation during stimulus presentation, despite higher temporal variability. Overall, EyeTheia provides a transparent and extensible solution for low-cost gaze tracking, suitable for scalable and reproducible experimental and clinical studies. The code, trained models, and experimental materials are publicly available.",
"arxiv_id": "2601.06279",
"authors": [
"Stevenson Pather",
"Niels Martign\u00e8ne",
"Arnaud Bugnet",
"Fouad Boutaleb",
"Fabien D\u0027Hondt",
"Deise Santana Maia"
],
"categories": [
"cs.CV"
],
"license": "http://creativecommons.org/licenses/by/4.0/",
"title": "EyeTheia: A Lightweight and Accessible Eye-Tracking Toolbox",
"url": "https://arxiv.org/abs/2601.06279",
"version": "v1"
},
"schema_id": "dorsal/arxiv",
"source": {
"execution_id": "d7e69e5a-4e8e-4e63-8985-64cf89eb65f4",
"id": "arXiv Dataset",
"type": "Model",
"variant": "snapshot-2026-01-17",
"version": "0.1.0"
},
"user_id": 1000002
}