论文标题
Haze Net：低分辨率面部图像中的高频专注于超级分辨的凝视估计
HAZE-Net: High-Frequency Attentive Super-Resolved Gaze Estimation in Low-Resolution Face Images
论文作者
论文摘要
尽管已经通过深度学习技术开发了凝视估计方法，但没有采取诸如以50像素或更少的像素宽度或更少的像素宽度的低分辨率面部图像中获得准确性能的方法。为了在具有挑战性的低分辨率条件下解决一个限制，我们提出了高频专注的超级分辨凝视估计网络，即雾糊状网络。我们的网络改善了输入图像的分辨率，并通过基于高频注意块的建议的超分辨率模块增强了眼睛特征和这些边界。此外，我们的凝视估计模块利用眼睛的高频组件以及全球外观图。我们还利用面部的结构位置信息来近似头姿势。实验结果表明，即使在具有28x28像素的低分辨率面部图像中，提出的方法也表现出强大的凝视估计性能。该工作的源代码可在https://github.com/dbseorms16/haze_net/上获得。
Although gaze estimation methods have been developed with deep learning techniques, there has been no such approach as aim to attain accurate performance in low-resolution face images with a pixel width of 50 pixels or less. To solve a limitation under the challenging low-resolution conditions, we propose a high-frequency attentive super-resolved gaze estimation network, i.e., HAZE-Net. Our network improves the resolution of the input image and enhances the eye features and those boundaries via a proposed super-resolution module based on a high-frequency attention block. In addition, our gaze estimation module utilizes high-frequency components of the eye as well as the global appearance map. We also utilize the structural location information of faces to approximate head pose. The experimental results indicate that the proposed method exhibits robust gaze estimation performance even in low-resolution face images with 28x28 pixels. The source code of this work is available at https://github.com/dbseorms16/HAZE_Net/.
