用普通摄像头实现低成本实时眼动追踪，适合科研与临床应用。
EyeTheia: A Lightweight and Accessible Eye-Tracking Toolbox
- 基于MediaPipe和轻量CNN，结合用户微调提升精度。
- 无需校准即可达与商用工具相当的左右注视判断准确率。
- 开源可复现，适合大规模实验和真实场景研究。
我们提出EyeTheia，一个轻量级、开源的基于网络摄像头的眼动估计深度学习流程，专为浏览器实验平台及真实世界的认知与临床研究设计。该系统仅需标准笔记本摄像头即可实现实时眼动追踪，结合MediaPipe人脸关键点提取与受iTracker启发的卷积神经网络，并支持用户特定微调。我们比较了两种策略：在移动端数据上预训练模型，以及在桌面端数据集上从头训练相同架构。在MPIIFaceGaze上的验证显示，两者未校准时性能相当，而轻量级用户微调始终能降低眼动预测误差。进一步在真实世界的点探测任务中评估，结果表明其左右注视分配与商业工具SeeSo SDK高度一致，尽管时间分辨率略低。整体而言，EyeTheia提供了一个透明且可扩展的低成本眼动追踪方案，适用于可扩展、可复现的实验与临床研究。代码、训练模型及实验材料均已公开。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。