FlatTrack: Eye-tracking with ultra-thin lensless cameras

TL;DR

This paper introduces FlatTrack, a compact, lensless eye gaze tracking system that is ultra-flat, lightweight, and capable of real-time performance, suitable for integration into AR/VR headsets.

Contribution

The work presents a novel lensless, mask-based camera design combined with a deep neural network for ultra-flat, high-performance eye gaze tracking in wearable devices.

Findings

Performs on par with traditional lens-based trackers

Achieves real-time gaze tracking at over 125 fps

Significantly reduces the form factor of eye trackers

Abstract

Existing eye trackers use cameras based on thick compound optical elements, necessitating the cameras to be placed at focusing distance from the eyes. This results in the overall bulk of wearable eye trackers, especially for augmented and virtual reality (AR/VR) headsets. We overcome this limitation by building a compact flat eye gaze tracker using mask-based lensless cameras. These cameras, in combination with co-designed lightweight deep neural network algorithm, can be placed in extreme close proximity to the eye, within the eyeglasses frame, resulting in ultra-flat and lightweight eye gaze tracker system. We collect a large dataset of near-eye lensless camera measurements along with their calibrated gaze directions for training the gaze tracking network. Through real and simulation experiments, we show that the proposed gaze tracking system performs on par with conventional lens-based trackers while maintaining a significantly flatter and more compact form-factor. Moreover, our gaze regressor boasts real-time (>125 fps) performance for gaze tracking.