PEGASUS：具有可组合属性的个性化生成式3D头像
PEGASUS: Personalized Generative 3D Avatars with Composable Attributes
AI总结：
PEGASUS从单目视频构建个性化生成式3D人脸头像，通过合成数据库和个性化生成模型实现解耦的面部属性编辑，在保持身份的同时达到高真实感，并提出零样本方法提升效率。
摘要：
我们提出PEGASUS，一种从单目视频源构建个性化生成式3D人脸头像的方法。我们的生成式3D头像支持解耦控制，能够在保持身份不变的同时选择性地改变面部属性（例如头发或鼻子）。我们的方法包含两个阶段：合成数据库生成和构建个性化生成式头像。我们生成目标身份在不同面部属性变化下的合成视频集合，这些视频通过借用不同身份单目视频中的属性来合成。然后，我们构建一个特定于个人的生成式3D头像，它可以在保持身份的同时连续修改其属性。通过大量实验，我们证明我们生成合成数据库并创建3D生成式头像的方法在保持身份的同时实现高真实感方面最为有效。随后，我们引入一种零样本方法，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目标。
英文摘要：
We present PEGASUS, a method for constructing a personalized generative 3D face avatar from monocular video sources. Our generative 3D avatar enables disentangled controls to selectively alter the facial attributes (e.g., hair or nose) while preserving the identity. Our approach consists of two stages: synthetic database generation and constructing a personalized generative avatar. We generate a synthetic video collection of the target identity with varying facial attributes, where the videos are synthesized by borrowing the attributes from monocular videos of diverse identities. Then, we build a person-specific generative 3D avatar that can modify its attributes continuously while preserving its identity. Through extensive experiments, we demonstrate that our method of generating a synthetic database and creating a 3D generative avatar is the most effective in preserving identity while achieving high realism. Subsequently, we introduce a zero-shot approach to achieve the same goal of generative modeling more efficiently by leveraging a previously constructed personalized generative model.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
