论文标题
自我学习的转变，以改善目光和重定向
Self-Learning Transformations for Improving Gaze and Head Redirection
论文作者
论文摘要
许多计算机视觉任务依赖于标记的数据。生成建模的快速进步已导致能够合成逼真的图像。但是，控制生成过程的特定方面，以便可以将数据用于监督下游任务仍然具有挑战性。在本文中，我们提出了一种用于面部图像的新型生成模型，该模型能够在眼睛注视和头部方向角度的细粒度控制下产生高质量的图像。这就需要解散许多与外观相关的因素，包括凝视和头部方向，以及照明，色调等。我们提出了一种新型的建筑，该建筑学会以自学方式发现，解开和编码这些无关的变体。我们进一步表明，明确解开任务 - 无关的因素会导致更准确的凝视和头部方向建模。一种新颖的评估方案表明，我们的方法在重定向准确性和凝视方向和头部方向变化之间的脱离精度和分离方面有所改善。此外，我们表明，在存在有限数量的实际训练数据的情况下，我们的方法可以改善半监视的跨数据库估算的下游任务。请在以下网址查看我们的项目页面：https：//ait.ethz.ch/projects/2020/sted-gaze/
Many computer vision tasks rely on labeled data. Rapid progress in generative modeling has led to the ability to synthesize photorealistic images. However, controlling specific aspects of the generation process such that the data can be used for supervision of downstream tasks remains challenging. In this paper we propose a novel generative model for images of faces, that is capable of producing high-quality images under fine-grained control over eye gaze and head orientation angles. This requires the disentangling of many appearance related factors including gaze and head orientation but also lighting, hue etc. We propose a novel architecture which learns to discover, disentangle and encode these extraneous variations in a self-learned manner. We further show that explicitly disentangling task-irrelevant factors results in more accurate modelling of gaze and head orientation. A novel evaluation scheme shows that our method improves upon the state-of-the-art in redirection accuracy and disentanglement between gaze direction and head orientation changes. Furthermore, we show that in the presence of limited amounts of real-world training data, our method allows for improvements in the downstream task of semi-supervised cross-dataset gaze estimation. Please check our project page at: https://ait.ethz.ch/projects/2020/STED-gaze/
