论文标题
任务不合时宜的面部视频编辑
Task-agnostic Temporally Consistent Facial Video Editing
论文作者
论文摘要
最近的研究见证了面部图像编辑任务的进步。但是，对于视频编辑，以前的方法要么简单地通过框架应用转换框架，要么以串联或迭代的方式使用多个帧，从而导致明显的视觉闪烁。此外，这些方法仅限于一次处理一项特定任务而没有任何可扩展性。在本文中，我们提出了一个任务不合时宜的面部视频编辑框架。基于3D重建模型，我们的框架旨在以更统一和分离的方式处理多个编辑任务。核心设计包括动态训练样本选择机制和新颖的3D时间损失约束，该损失限制完全利用图像和视频数据集并实现时间一致性。与最先进的面部图像编辑方法相比，我们的框架生成的视频肖像更现实，并且在时间上平稳。
Recent research has witnessed the advances in facial image editing tasks. For video editing, however, previous methods either simply apply transformations frame by frame or utilize multiple frames in a concatenated or iterative fashion, which leads to noticeable visual flickers. In addition, these methods are confined to dealing with one specific task at a time without any extensibility. In this paper, we propose a task-agnostic temporally consistent facial video editing framework. Based on a 3D reconstruction model, our framework is designed to handle several editing tasks in a more unified and disentangled manner. The core design includes a dynamic training sample selection mechanism and a novel 3D temporal loss constraint that fully exploits both image and video datasets and enforces temporal consistency. Compared with the state-of-the-art facial image editing methods, our framework generates video portraits that are more photo-realistic and temporally smooth.
