We present, PEGASUS, a method for constructing personalized generative 3D face avatars from monocular video sources. As a compositional generative model, our model enables disentangled controls to selectively alter the facial attributes (e.g., hair or nose) of the target individual, while preserving the identity. We present two key approaches to achieve this goal. First, we present a method to construct a person-specific generative 3D avatar by building a synthetic video collection of the target identity with varying facial attributes, where the videos are synthesized by borrowing parts from diverse individuals from other monocular videos. Through several experiments, we demonstrate the superior performance of our approach by generating unseen attributes with high realism. Subsequently, we introduce a zero-shot approach to achieve the same generative modeling more efficiently by leveraging a previously constructed personalized generative model.

翻译：我们提出PEGASUS方法，一种从单目视频源构建个性化生成式三维面部化身的技术。作为组合生成模型，我们的模型能够实现解耦控制，在保持身份特征的同时选择性改变目标个体的面部属性（例如发型或鼻型）。为实现这一目标，我们提出两种关键方法。首先，我们通过构建目标身份带有不同面部属性的合成视频集来建立个体专属生成式三维化身，这些视频通过从其他单目视频中的不同个体"借取"面部部位合成。通过多组实验，我们证明了该方法在生成未见属性时的高逼真度与优越性能。随后，我们引入零样本方法，通过利用先前构建的个性化生成模型，更高效地实现相同的生成建模能力。