# Precise localization of corneal reflections in eye images using deep learning trained on synthetic data

arXiv: https://arxiv.org/abs/2304.05673 · HTML: https://mlsanity.com/paper/2304.05673/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 7 of its 48 references that are in the map.
- First posted on arXiv 12 Apr 2023.

## Builds on (most cited first, 7 of 7)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Learning from Simulated and Unsupervised Images through Adversarial Training](https://mlsanity.com/paper/1612.07828/) (2016)
- [Appearance-based Gaze Estimation With Deep Learning: A Review and Benchmark](https://mlsanity.com/paper/2104.12668/) (2021)
- [Rendering of Eyes for Eye-Shape Registration and Gaze Estimation](https://mlsanity.com/paper/1505.05916/) (2015)
- [PupilNet v2.0: Convolutional Neural Networks for CPU based real time Robust Pupil Detection](https://mlsanity.com/paper/1711.00112/) (2017)
- [Geometric deep learning reveals the spatiotemporal fingerprint of microscopic motion](https://mlsanity.com/paper/2202.06355/) (2022)
- [Quantitative Digital Microscopy with Deep Learning](https://mlsanity.com/paper/2010.08260/) (2020)

## Built on by (most cited first, 4 of 4)

- [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)
- [Zero-Shot Pupil Segmentation with SAM 2: A Case Study of Over 14 Million Images](https://mlsanity.com/paper/2410.08926/) (2024)
- [Night Eyes: A Reproducible Framework for Constellation-Based Corneal Reflection Matching](https://mlsanity.com/paper/2604.01909/) (2026)

## Abstract (arXiv)

We present a deep learning method for accurately localizing the center of a single corneal reflection (CR) in an eye image. Unlike previous approaches, we use a convolutional neural network (CNN) that was trained solely using simulated data. Using only simulated data has the benefit of completely sidestepping the time-consuming process of manual annotation that is required for supervised training on real eye images. To systematically evaluate the accuracy of our method, we first tested it on images with simulated CRs placed on different backgrounds and embedded in varying levels of noise. Second, we tested the method on high-quality videos captured from real eyes. Our method outperformed state-of-the-art algorithmic methods on real eye images with a 35% reduction in terms of spatial precision, and performed on par with state-of-the-art on simulated images in terms of spatial accuracy.We conclude that our method provides a precise method for CR center localization and provides a solution to the data availability problem which is one of the important common roadblocks in the development of deep learning models for gaze estimation. Due to the superior CR center localization and ease of application, our method has the potential to improve the accuracy and precision of CR-based eye trackers