WEBEYETRACK: Scalable Eye-Tracking for the Browser via On-Device Few-Shot Personalization

TL;DR

WebEyeTrack is a browser-based eye-tracking framework that uses lightweight models and on-device few-shot learning to achieve state-of-the-art accuracy, real-time performance, and user personalization while addressing privacy concerns.

Contribution

It introduces a scalable, privacy-preserving eye-tracking method that combines lightweight models, head pose estimation, and few-shot learning directly in the browser.

Findings

Achieves 2.32 cm error on GazeCapture dataset.

Real-time inference at 2.4 ms on iPhone 14.

Effective user adaptation with fewer than nine calibration samples.

Abstract

With advancements in AI, new gaze estimation methods are exceeding state-of-the-art (SOTA) benchmarks, but their real-world application reveals a gap with commercial eye-tracking solutions. Factors like model size, inference time, and privacy often go unaddressed. Meanwhile, webcam-based eye-tracking methods lack sufficient accuracy, in particular due to head movement. To tackle these issues, we introduce We bEyeTrack, a framework that integrates lightweight SOTA gaze estimation models directly in the browser. It incorporates model-based head pose estimation and on-device few-shot learning with as few as nine calibration samples (k < 9). WebEyeTrack adapts to new users, achieving SOTA performance with an error margin of 2.32 cm on GazeCapture and real-time inference speeds of 2.4 milliseconds on an iPhone 14. Our open-source code is available at https://github.com/RedForestAi/WebEyeTrack.