Gaze tracking is an essential component of next generation displays for virtual reality and augmented reality applications. Traditional camera-based gaze trackers used in next generation displays are known to be lacking in one or multiple of the following metrics: power consumption, cost, computational complexity, estimation accuracy, latency, and form-factor. We propose the use of discrete photodiodes and light-emitting diodes (LEDs) as an alternative to traditional camera-based gaze tracking approaches while taking all of these metrics into consideration. We begin by developing a rendering-based simulation framework for understanding the relationship between light sources and a virtual model eyeball. Findings from this framework are used for the placement of LEDs and photodiodes. Our first prototype uses a neural network to obtain an average error rate of 2.67{\deg} at 400Hz while demanding only 16mW. By simplifying the implementation to using only LEDs, duplexed as light transceivers, and more minimal machine learning model, namely a light-weight supervised Gaussian process regression algorithm, we show that our second prototype is capable of an average error rate of 1.57{\deg} at 250 Hz using 800 mW.

中文翻译：

---

使用空间稀疏单像素探测器进行光学凝视跟踪

视线跟踪是用于虚拟现实和增强现实应用的下一代显示器的重要组成部分。众所周知，下一代显示器中使用的传统基于摄像头的凝视跟踪器缺乏以下一项或多项指标：功耗、成本、计算复杂性、估计精度、延迟和外形因素。我们建议使用分立光电二极管和发光二极管 (LED) 作为传统基于相机的凝视跟踪方法的替代方案，同时考虑所有这些指标。我们首先开发一个基于渲染的模拟框架来理解光源和虚拟模型眼球之间的关系。该框架的结果用于放置 LED 和光电二极管。我们的第一个原型使用神经网络在 400Hz 下获得 2.67{\deg} 的平均错误率，同时仅需要 16mW。通过将实现简化为仅使用 LED，双工作为光收发器，以及更小的机器学习模型，即轻量级监督高斯过程回归算法，我们表明我们的第二个原型能够实现 1.57{\deg } 在 250 Hz 时使用 800 mW。