We present a novel multistream network that learns robust eye representations for gaze estimation. We first create a synthetic dataset containing eye region masks detailing the visible eyeball and iris using a simulator. We then perform eye region segmentation with a U-Net type model which we later use to generate eye region masks for real-world eye images. Next, we pretrain an eye image encoder in the real domain with self-supervised contrastive learning to learn generalized eye representations. Finally, this pretrained eye encoder, along with two additional encoders for visible eyeball region and iris, are used in parallel in our multistream framework to extract salient features for gaze estimation from real-world images. We demonstrate the performance of our method on the EYEDIAP dataset in two different evaluation settings and achieve state-of-the-art results, outperforming all the existing benchmarks on this dataset. We also conduct additional experiments to validate the robustness of our self-supervised network with respect to different amounts of labeled data used for training.

翻译：我们展示了一个新颖的多流网络, 学会如何用眼睛来进行视觉估计。 我们首先创建了一个合成数据集, 包含眼睛区域面罩, 详细描述可见眼球和虹膜。 然后我们用一个 U-Net 型模型进行眼区域分割, 我们随后用这个模型来生成真实世界眼图像的眼区域面罩。 接下来, 我们用自我监督的对比学习在真实域预设一个眼睛图像编码器, 学习一般眼表解。 最后, 这个预先训练的眼镜编码器, 以及另外两个可见眼区域和虹膜的编码器, 在我们的多流框架中同时使用, 来从真实世界图像中提取视觉估计的显著特征。 我们展示了我们在两个不同的评估环境中的EMEDIAP数据集方法的性能, 并取得了最新的结果, 超过了这个数据集上的所有现有基准。 我们还进行了更多的实验, 以验证我们自我监督的网络在用于培训的标签数据数量上是否稳健。