我的时间机器：个性化面部年龄转换

MyTimeMachine: Personalized Facial Age Transformation

November 21, 2024

作者: Luchao Qi, Jiaye Wu, Bang Gong, Annie N. Wang, David W. Jacobs, Roni Sengupta

cs.AI

摘要

面部老化是一个复杂的过程，高度依赖于诸如性别、种族、生活方式等多种因素，因此对于准确预测个体的老化而言，学习全局老化先验是极具挑战性的。现有技术通常能够产生逼真且合理的老化结果，但重新老化的图像往往不像目标年龄时个人的外貌，因此需要个性化。在许多虚拟老化的实际应用中，例如电影和电视节目中的视觉特效，用户的个人照片收藏通常展现了一个较短时间间隔（20至40年）内的老化过程。然而，对个人照片收藏进行全局老化技术的朴素个性化尝试通常会失败。因此，我们提出了MyTimeMachine（MyTM），它将全局老化先验与个人照片收藏（最少使用50张图像）相结合，以学习个性化的年龄转换。我们引入了一种新型适配器网络，将个性化老化特征与全局老化特征结合起来，并使用StyleGAN2生成一个重新老化的图像。我们还引入了三种损失函数，用于通过个性化老化损失、外推正则化和自适应w-范数正则化来个性化适配器网络。我们的方法还可以扩展到视频，实现高质量、保持身份特征和时间上一致的老化效果，使其与目标年龄的实际外貌相似，展示了其优于现有技术的优越性。

English

Facial aging is a complex process, highly dependent on multiple factors like gender, ethnicity, lifestyle, etc., making it extremely challenging to learn a global aging prior to predict aging for any individual accurately. Existing techniques often produce realistic and plausible aging results, but the re-aged images often do not resemble the person's appearance at the target age and thus need personalization. In many practical applications of virtual aging, e.g. VFX in movies and TV shows, access to a personal photo collection of the user depicting aging in a small time interval (20sim40 years) is often available. However, naive attempts to personalize global aging techniques on personal photo collections often fail. Thus, we propose MyTimeMachine (MyTM), which combines a global aging prior with a personal photo collection (using as few as 50 images) to learn a personalized age transformation. We introduce a novel Adapter Network that combines personalized aging features with global aging features and generates a re-aged image with StyleGAN2. We also introduce three loss functions to personalize the Adapter Network with personalized aging loss, extrapolation regularization, and adaptive w-norm regularization. Our approach can also be extended to videos, achieving high-quality, identity-preserving, and temporally consistent aging effects that resemble actual appearances at target ages, demonstrating its superiority over state-of-the-art approaches.