EyeTheia: A Lightweight and Accessible Eye-Tracking Toolbox

TL;DR

EyeTheia is a lightweight, open-source deep learning toolbox for real-time webcam-based gaze estimation, suitable for browser-based experiments and clinical research, offering comparable accuracy to commercial solutions.

Contribution

It introduces a novel, accessible gaze-tracking pipeline combining MediaPipe landmarks with CNNs, and evaluates strategies for model adaptation and fine-tuning.

Findings

Comparable performance of pretrained and from-scratch models on MPIIFaceGaze

User-specific fine-tuning reduces gaze prediction error

Strong agreement with commercial gaze tracker in stimulus tasks

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.