# PupilNet: Convolutional Neural Networks for Robust Pupil Detection

arXiv: https://arxiv.org/abs/1601.04902 · HTML: https://mlsanity.com/paper/1601.04902/

## Key facts

- Cited by 20 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 19 Jan 2016.

## Built on by (most cited first, 20 of 20)

- [TEyeD: Over 20 million real-world eye images with Pupil, Eyelid, and Iris 2D and 3D Segmentations, 2D and 3D Landmarks, 3D Eyeball, Gaze Vector, and Eye Movement Types](https://mlsanity.com/paper/2102.02115/) (2021)
- [The Gaze and Mouse Signal as additional Source for User Fingerprints in Browser Applications](https://mlsanity.com/paper/2101.03793/) (2021)
- [Co-designing a Sub-millisecond Latency Event-based Eye Tracking System with Submanifold Sparse CNN](https://mlsanity.com/paper/2404.14279/) (2024)
- [A Multimodal Eye Movement Dataset and a Multimodal Eye Movement Segmentation Analysis](https://mlsanity.com/paper/2101.04318/) (2021)
- [1000 Pupil Segmentations in a Second using Haar Like Features and Statistical Learning](https://mlsanity.com/paper/2102.01921/) (2021)
- [Zero-Shot Segmentation of Eye Features Using the Segment Anything Model (SAM)](https://mlsanity.com/paper/2311.08077/) (2023)
- [Maximum and Leaky Maximum Propagation](https://mlsanity.com/paper/2105.10277/) (2021)
- [LEyes: A Lightweight Framework for Deep Learning-Based Eye Tracking using Synthetic Eye Images](https://mlsanity.com/paper/2309.06129/) (2023)
- [Tensor Normalization and Full Distribution Training](https://mlsanity.com/paper/2109.02345/) (2021)
- [GroupGazer: A Tool to Compute the Gaze per Participant in Groups with integrated Calibration to Map the Gaze Online to a Screen or Beamer Projection](https://mlsanity.com/paper/2201.07692/) (2022)
- [Zero-Shot Pupil Segmentation with SAM 2: A Case Study of Over 14 Million Images](https://mlsanity.com/paper/2410.08926/) (2024)
- [Towards Everyday Virtual Reality through Eye Tracking](https://mlsanity.com/paper/2203.15703/) (2022)
- [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)
- [Technical Report: Combining knowledge from Transfer Learning during training and Wide Resnets](https://mlsanity.com/paper/2206.09697/) (2022)
- [An Embedded and Real-Time Pupil Detection Pipeline](https://mlsanity.com/paper/2302.14098/) (2023)
- [A temporally quantized distribution of pupil diameters as a new feature for cognitive load classification](https://mlsanity.com/paper/2303.12757/) (2023)
- [Normalized Validity Scores for DNNs in Regression based Eye Feature Extraction](https://mlsanity.com/paper/2403.11665/) (2024)
- [EyeSeg: An Uncertainty-Aware Eye Segmentation Framework for AR/VR](https://mlsanity.com/paper/2507.09649/) (2025)
- [Eye image segmentation using visual and concept prompts with Segment Anything Model 3 (SAM3)](https://mlsanity.com/paper/2603.17715/) (2026)

## Abstract (arXiv)

Real-time, accurate, and robust pupil detection is an essential prerequisite for pervasive video-based eye-tracking. However, automated pupil detection in real-world scenarios has proven to be an intricate challenge due to fast illumination changes, pupil occlusion, non centered and off-axis eye recording, and physiological eye characteristics. In this paper, we propose and evaluate a method based on a novel dual convolutional neural network pipeline. In its first stage the pipeline performs coarse pupil position identification using a convolutional neural network and subregions from a downscaled input image to decrease computational costs. Using subregions derived from a small window around the initial pupil position estimate, the second pipeline stage employs another convolutional neural network to refine this position, resulting in an increased pupil detection rate up to 25% in comparison with the best performing state-of-the-art algorithm. Annotated data sets can be made available upon request.