# PuRe: Robust pupil detection for real-time pervasive eye tracking

arXiv: https://arxiv.org/abs/1712.08900 · HTML: https://mlsanity.com/paper/1712.08900/

## Key facts

- Cited by 17 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 24 Dec 2017.

## Built on by (most cited first, 17 of 17)

- [A Review of Driver Gaze Estimation and Application in Gaze Behavior Understanding](https://mlsanity.com/paper/2307.01470/) (2023)
- [LAD: A Hybrid Deep Learning System for Benign Paroxysmal Positional Vertigo Disorders Diagnostic](https://mlsanity.com/paper/2210.08282/) (2022)
- [Zero-Shot Segmentation of Eye Features Using the Segment Anything Model (SAM)](https://mlsanity.com/paper/2311.08077/) (2023)
- [LEyes: A Lightweight Framework for Deep Learning-Based Eye Tracking using Synthetic Eye Images](https://mlsanity.com/paper/2309.06129/) (2023)
- [CondSeg: Ellipse Estimation of Pupil and Iris via Conditioned Segmentation](https://mlsanity.com/paper/2408.17231/) (2024)
- [Towards Unsupervised Eye-Region Segmentation for Eye Tracking](https://mlsanity.com/paper/2410.06131/) (2024)
- [Zero-Shot Pupil Segmentation with SAM 2: A Case Study of Over 14 Million Images](https://mlsanity.com/paper/2410.08926/) (2024)
- [Using Deep Learning to Increase Eye-Tracking Robustness, Accuracy, and Precision in Virtual Reality](https://mlsanity.com/paper/2403.19768/) (2024)
- [High-frequency near-eye ground truth for event-based eye tracking](https://mlsanity.com/paper/2502.03057/) (2025)
- [Bayesian Eye Tracking](https://mlsanity.com/paper/2106.13387/) (2021)
- [Slippage-robust Gaze Tracking for Near-eye Display](https://mlsanity.com/paper/2210.11637/) (2022)
- [An Embedded and Real-Time Pupil Detection Pipeline](https://mlsanity.com/paper/2302.14098/) (2023)
- [Normalized Validity Scores for DNNs in Regression based Eye Feature Extraction](https://mlsanity.com/paper/2403.11665/) (2024)
- [Realizing Fully-Integrated, Low-Power, Event-Based Pupil Tracking with Neuromorphic Hardware](https://mlsanity.com/paper/2511.20175/) (2025)
- [An Affordable, Wearable Stereo-Eye-Tracking Platform](https://mlsanity.com/paper/2604.24331/) (2026)
- [AmbientEye: A Dataset for Pupil Segmentation under Natural Ambient Infrared Illumination](https://mlsanity.com/paper/2606.03774/) (2026)
- [GenEyePose: Patient-Free, Knowledge-Based Saccadic Eye Movement Modeling for Digital Neurophysiologic Biomarker Development](https://mlsanity.com/paper/2606.09681/) (2026)

## Abstract (arXiv)

Real-time, accurate, and robust pupil detection is an essential prerequisite to enable pervasive eye-tracking and its applications -- e.g., gaze-based human computer interaction, health monitoring, foveated rendering, and advanced driver assistance. However, automated pupil detection has proved to be an intricate task in real-world scenarios due to a large mixture of challenges such as quickly changing illumination and occlusions. In this paper, we introduce the Pupil Reconstructor PuRe, a method for pupil detection in pervasive scenarios based on a novel edge segment selection and conditional segment combination schemes; the method also includes a confidence measure for the detected pupil. The proposed method was evaluated on over 316,000 images acquired with four distinct head-mounted eye tracking devices. Results show a pupil detection rate improvement of over 10 percentage points w.r.t. state-of-the-art algorithms in the two most challenging data sets (6.46 for all data sets), further pushing the envelope for pupil detection. Moreover, we advance the evaluation protocol of pupil detection algorithms by also considering eye images in which pupils are not present. In this aspect, PuRe improved precision and specificity w.r.t. state-of-the-art algorithms by 25.05 and 10.94 percentage points, respectively, demonstrating the meaningfulness of PuRe's confidence measure. PuRe operates in real-time for modern eye trackers (at 120 fps).