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

arXiv: https://arxiv.org/abs/2508.19544 · HTML: https://mlsanity.com/paper/2508.19544/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 10 of its 27 references that are in the map.
- First posted on arXiv 27 Aug 2025.

## Builds on (most cited first, 10 of 10)

- [Towards Fast, Accurate and Stable 3D Dense Face Alignment](https://mlsanity.com/paper/2009.09960/) (2020)
- [TurkerGaze: Crowdsourcing Saliency with Webcam based Eye Tracking](https://mlsanity.com/paper/1504.06755/) (2015)
- [Eye Tracking for Everyone](https://mlsanity.com/paper/1606.05814/) (2016)
- [Appearance-Based Gaze Estimation in the Wild](https://mlsanity.com/paper/1504.02863/) (2015)
- [Appearance-based Gaze Estimation With Deep Learning: A Review and Benchmark](https://mlsanity.com/paper/2104.12668/) (2021)
- [Few-Shot Adaptive Gaze Estimation](https://mlsanity.com/paper/1905.01941/) (2019)
- [BlazeFace: Sub-millisecond Neural Face Detection on Mobile GPUs](https://mlsanity.com/paper/1907.05047/) (2019)
- [Attention Mesh: High-fidelity Face Mesh Prediction in Real-time](https://mlsanity.com/paper/2006.10962/) (2020)
- [Evaluation of Appearance-Based Methods and Implications for Gaze-Based Applications](https://mlsanity.com/paper/1901.10906/) (2019)
- [EFE: End-to-end Frame-to-Gaze Estimation](https://mlsanity.com/paper/2305.05526/) (2023)

## Built on by (most cited first, 1 of 1)

- [Low Latency Gaze Tracking via Latent Optical Sensing](https://mlsanity.com/paper/2605.17990/) (2026)

## Abstract (arXiv)

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.