Abstract
Although recent deep learning based gaze estimation approaches have achieved much improvement, we still know little about how gaze features are connected to the physics of gaze. In this paper, we try to answer this question by analyzing the gaze feature manifold. Our analysis revealed the insight that the geodesic distance between gaze features is consistent with the gaze differences between samples. According to this finding, we construct the Physics- Consistent Feature (PCF) in an analytical way, which connects gaze feature to the physical definition of gaze. We further propose the PCFGaze framework that directly optimizes gaze feature space by the guidance of PCF. Experimental results demonstrate that the proposed framework alleviates the overfitting problem and significantly improves cross-domain gaze estimation accuracy without extra training data. The insight of gaze feature has the potential to benefit other regression tasks with physical meanings.
Abstract (translated)
尽管近年来基于深度学习的 gaze 估计方法已经取得了很大进展,但我们仍然对 gaze 特征与 gaze 物理之间的关系了解不足。在本文中,我们试图通过分析 gaze 特征万维网来回答这个问题。我们的分析揭示了 gaze 特征之间的葛氏距离与样本之间的 gaze 差异是一致的。根据这一发现,我们采用一种分析的方法来构建具有物理一致性的特征(PCF),该特征将 gaze 特征与 gaze 的物理定义联系起来。我们还提出了 PCFGaze 框架,该框架通过 PCF 的指导直接优化 gaze 特征空间。实验结果显示,该框架可以减轻过拟合问题并显著改善跨域的 gaze 估计准确性,而 gaze 特征的意识能够为其他具有物理意义的回归任务带来好处。
URL
https://arxiv.org/abs/2309.02165
