Abstract
Face aging or de-aging with generative AI has gained significant attention for its applications in such fields like forensics, security, and media. However, most state of the art methods rely on conditional Generative Adversarial Networks (GANs), Diffusion-based models, or Visual Language Models (VLMs) to age or de-age faces based on predefined age categories and conditioning via loss functions, fine-tuning, or text prompts. The reliance on such conditioning leads to complex training requirements, increased data needs, and challenges in generating consistent results. Additionally, identity preservation is rarely taken into accountor evaluated on a single face recognition system without any control or guarantees on whether identity would be preserved in a generated aged/de-aged face. In this paper, we propose to synthesize aged and de-aged faces via editing latent space of StyleGAN2 using a simple support vector modeling of aging/de-aging direction and several feature selection approaches. By using two state-of-the-art face recognition systems, we empirically find the identity preserving subspace within the StyleGAN2 latent space, so that an apparent age of a given face can changed while preserving the identity. We then propose a simple yet practical formula for estimating the limits on aging/de-aging parameters that ensures identity preservation for a given input face. Using our method and estimated parameters we have generated a public dataset of synthetic faces at different ages that can be used for benchmarking cross-age face recognition, age assurance systems, or systems for detection of synthetic images. Our code and dataset are available at the project page this https URL
Abstract (translated)
使用生成人工智能进行面部老化或逆向老化技术，在法医、安全和媒体等领域得到了广泛的关注。然而，大多数最先进的方法依赖于条件生成对抗网络（GAN）、基于扩散的模型或视觉语言模型（VLM），通过预定义的年龄类别以及损失函数、微调或文本提示等方式来进行面部的老化或逆向老化处理。这种依赖条件设定的方法会导致复杂的训练要求，增加数据需求，并且在生成一致结果方面存在挑战。此外，在单一人脸识别系统中很少考虑或评估身份保持问题，即无法保证生成的老化或逆向老化后的脸部图像能够保留原有的身份信息。 在这篇论文中，我们提出了一种通过编辑StyleGAN2的潜在空间来合成老化和逆向老化的面部的方法。我们在潜在空间中使用了简单的支持向量模型来描述老化/逆向老化的方向，并采用了几种特征选择方法。通过利用两种最先进的面部识别系统，我们从实验上找到了能够保持身份一致性的子空间，使给定的面部图像能够在改变外观年龄的同时保留其身份信息。随后，我们提出了一种简单的计算公式，用于估算确保在处理过程中身份不会丢失的老化/逆向老化参数范围。使用我们的方法和估计出的参数，我们生成了一个公开的人脸合成数据集，包含了不同年龄段的数据样本，可用于跨年龄段人脸识别、年龄验证系统或检测合成图像系统的基准测试。 项目的代码和数据集可以在以下链接获取：[请在此处填写实际提供的项目页面URL]
URL
https://arxiv.org/abs/2508.08808
