Subject Guided Eye Image Synthesis with Application to Gaze Redirection
Subject Guided Eye Image Synthesis with Application to Gaze Redirection
复制标题
DOI：
10.1109/wacv48630.2021.00006
复制
发表时间：
2021-01
期刊：
影响因子：
--
通讯作者：
Harsimran Kaur;R. Manduchi
中科院分区：
文献类型：
--
作者：
Harsimran Kaur;R. Manduchi
我们提出了一种方法，用于合成眼睛图像的分割掩模与所需的风格。该风格包括诸如肤色、纹理、虹膜颜色和个人身份等属性。我们的方法生成的眼睛图像是一致的给定的分割掩模，并具有输入样式图像的属性。我们将我们的方法应用于数据增强以及视线重定向。从合成眼睛图像合成真实的眼睛图像以用于数据增强的先前技术缺乏对所生成的属性的控制。我们证明了所提出的方法的有效性，在合成现实的眼睛图像与给定的特性对应的合成标签的数据增强，这是进一步有用的各种任务，如凝视估计，眼睛图像分割，瞳孔检测等，我们还展示了我们的方法可以应用到视线重定向只使用合成的凝视标签，提高了以前的最先进的结果。我们的论文的主要贡献是i）一种新的方法，用于基于风格的眼睛图像生成的分割掩模; ii）使用这种方法的凝视重定向，而不需要凝视注释的真实的眼睛图像
We propose a method for synthesizing eye images from segmentation masks with a desired style. The style encompasses attributes such as skin color, texture, iris color, and personal identity. Our approach generates an eye image that is consistent with a given segmentation mask and has the attributes of the input style image. We apply our method to data augmentation as well as to gaze redirection. The previous techniques of synthesizing real eye images from synthetic eye images for data augmentation lacked control over the generated attributes. We demonstrate the effectiveness of the proposed method in synthesizing realistic eye images with given characteristics corresponding to the synthetic labels for data augmentation, which is further useful for various tasks such as gaze estimation, eye image segmentation, pupil detection, etc. We also show how our approach can be applied to gaze redirection using only synthetic gaze labels, improving the previous state of the art results. The main contributions of our paper are i) a novel approach for Style-Based eye image generation from segmentation mask; ii) the use of this approach for gaze-redirection without the need for gaze annotated real eye images