Papers › Retina : Low-Power Eye Tracking with Event Camera and Spiking Hardware

Retina : Low-Power Eye Tracking with Event Camera and Spiking Hardware

1 Dec 2023arXiv:2312.00425archive 2025-07-28

Pietro Bonazzi, Sizhen Bian, Giovanni Lippolis, Yawei Li, Sadique Sheik, Michele Magno

This paper introduces a neuromorphic methodology for eye tracking, harnessing pure event data captured by a Dynamic Vision Sensor (DVS) camera. The framework integrates a directly trained Spiking Neuron Network (SNN) regression model and leverages a state-of-the-art low power edge neuromorphic processor - Speck, collectively aiming to advance the precision and efficiency of eye-tracking systems. First, we introduce a representative event-based eye-tracking dataset, "Ini-30", which was collected with two glass-mounted DVS cameras from thirty volunteers. Then,a SNN model, based on Integrate And Fire (IAF) neurons, named "Retina", is described , featuring only 64k parameters (6.63x fewer than the latest) and achieving pupil tracking error of only 3.24 pixels in a 64x64 DVS input. The continous regression output is obtained by means of convolution using a non-spiking temporal 1D filter slided across the output spiking layer. Finally, we evaluate Retina on the neuromorphic processor, showing an end-to-end power between 2.89-4.8 mW and a latency of 5.57-8.01 mS dependent on the time window. We also benchmark our model against the latest event-based eye-tracking method, "3ET", which was built upon event frames. Results show that Retina achieves superior precision with 1.24px less pupil centroid error and reduced computational complexity with 35 times fewer MAC operations. We hope this work will open avenues for further investigation of close-loop neuromorphic solutions and true event-based training pursuing edge performance.

PaperPDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

pbonazzi/retina officialmentioned in papermentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Pupil DetectionPupil Tracking

Datasets

Introduced by this paper, per the archive.

INI-30

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Pupil Detection INI-30 CNN Euclidean Distance 0.5 #1 of 2 Archive leaderboard report
Pupil Detection INI-30 TinyissimoV8 Euclidean Distance 1.75 #2 of 2 Archive leaderboard report
Pupil Tracking INI-30 Retina Euclidean Distance 3.24 #1 of 2 Archive leaderboard report
Pupil Tracking INI-30 3ET Euclidean Distance 4.48 #2 of 2 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

ConvolutionSNN

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections