Face views are particularly important in person-to-person communication. Differenes between the camera location and the face orientation can result in undesirable facial appearances of the participants during video conferencing. This phenomenon is particularly noticeable when using devices where the front-facing camera is placed in unconventional locations such as below the display or within the keyboard. In this paper, we take a video stream from a single RGB camera as input, and generate a video stream that emulates the view from a virtual camera at a designated location. The most challenging issue in this problem is that the corrected view often needs out-of-plane head rotations. To address this challenge, we reconstruct the 3D face shape and re-render it into synthesized frames according to the virtual camera location. To output the corrected video stream with natural appearance in real time, we propose several novel techniques including accurate eyebrow reconstruction, high-quality blending between the corrected face image and background, and template-based 3D reconstruction of glasses. Our system works well for different lighting conditions and skin tones, and can handle users wearing glasses. Extensive experiments and user studies demonstrate that our method provides high-quality results.

面对面的交流在人与人之间尤为重要。摄像机位置和面部朝向之间的差异可能会导致视频会议期间参与者的不良面部外观。当使用将前置摄像头放置在非常规位置（例如显示器下方或键盘内）的设备时，此现象尤其明显。在本文中，我们将来自单个RGB摄像机的视频流作为输入，并生成一个视频流，该视频流将模拟虚拟摄像机在指定位置的视图。此问题中最具挑战性的问题是，校正后的视图通常需要平面外旋转头部。为了解决这一挑战，我们重建了3D人脸形状，并根据虚拟相机的位置将其重新渲染为合成帧。为了实时输出具有自然外观的校正后的视频流，我们提出了几种新颖的技术，包括精确的眉毛重建，校正后的面部图像和背景之间的高质量混合以及基于模板的眼镜3D重建。我们的系统可以很好地适应不同的照明条件和肤色，并且可以处理戴眼镜的用户。大量的实验和用户研究表明，我们的方法可提供高质量的结果。