# GazeTrack: High-Precision Eye Tracking Based on Regularization and Spatial Computing

arXiv: https://arxiv.org/abs/2511.22607 · HTML: https://mlsanity.com/paper/2511.22607/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 9 of its 25 references that are in the map.
- First posted on arXiv 27 Nov 2025.

## Builds on (most cited first, 9 of 9)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [ETH-XGaze: A Large Scale Dataset for Gaze Estimation under Extreme Head Pose and Gaze Variation](https://mlsanity.com/paper/2007.15837/) (2020)
- [MPIIGaze: Real-World Dataset and Deep Appearance-Based Gaze Estimation](https://mlsanity.com/paper/1711.09017/) (2017)
- [MotionNet: Joint Perception and Motion Prediction for Autonomous Driving Based on Bird's Eye View Maps](https://mlsanity.com/paper/2003.06754/) (2020)
- [Star Shape Prior in Fully Convolutional Networks for Skin Lesion Segmentation](https://mlsanity.com/paper/1806.08437/) (2018)
- [Learning to Validate the Quality of Detected Landmarks](https://mlsanity.com/paper/1901.10143/) (2019)
- [Training Decision Trees as Replacement for Convolution Layers](https://mlsanity.com/paper/1905.10073/) (2019)
- [1000 Pupil Segmentations in a Second using Haar Like Features and Statistical Learning](https://mlsanity.com/paper/2102.01921/) (2021)

## Abstract (arXiv)

Eye tracking has become increasingly important in virtual and augmented reality applications; however, the current gaze accuracy falls short of meeting the requirements for spatial computing. We designed a gaze collection framework and utilized high-precision equipment to gather the first precise benchmark dataset, GazeTrack, encompassing diverse ethnicities, ages, and visual acuity conditions for pupil localization and gaze tracking. We propose a novel shape error regularization method to constrain pupil ellipse fitting and train on open-source datasets, enhancing semantic segmentation and pupil position prediction accuracy. Additionally, we invent a novel coordinate transformation method similar to paper unfolding to accurately predict gaze vectors on the GazeTrack dataset. Finally, we built a gaze vector generation model that achieves reduced gaze angle error with lower computational complexity compared to other methods.