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

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Davalos, Eduardo, Zhang, Yike, Srivastava, Namrata, Thatigotla, Yashvitha, Salas, Jorge A., McFadden, Sara, Cho, Sun-Joo, Goodwin, Amanda, TS, Ashwin, Biswas, Gautam
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909755093549056
author Davalos, Eduardo
Zhang, Yike
Srivastava, Namrata
Thatigotla, Yashvitha
Salas, Jorge A.
McFadden, Sara
Cho, Sun-Joo
Goodwin, Amanda
TS, Ashwin
Biswas, Gautam
author_facet Davalos, Eduardo
Zhang, Yike
Srivastava, Namrata
Thatigotla, Yashvitha
Salas, Jorge A.
McFadden, Sara
Cho, Sun-Joo
Goodwin, Amanda
TS, Ashwin
Biswas, Gautam
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2508_19544
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle WEBEYETRACK: Scalable Eye-Tracking for the Browser via On-Device Few-Shot Personalization
Davalos, Eduardo
Zhang, Yike
Srivastava, Namrata
Thatigotla, Yashvitha
Salas, Jorge A.
McFadden, Sara
Cho, Sun-Joo
Goodwin, Amanda
TS, Ashwin
Biswas, Gautam
Computer Vision and Pattern Recognition
Artificial Intelligence
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.
title WEBEYETRACK: Scalable Eye-Tracking for the Browser via On-Device Few-Shot Personalization
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2508.19544