用扩散模型去除人脸妆容，提升年龄识别准确率。
DiffClean: Diffusion-based Makeup Removal for Accurate Age Estimation
- 用文本引导的扩散模型去除妆容痕迹。
- 年龄判断准确率提升5.8%，人脸验证误报率降低5.1%。
- 适用于真实与模拟妆容，适合安全验证场景。
准确的年龄验证可保护未成年人免受需年龄限制的在线平台和电商服务的不当访问。然而，面部妆容会改变外貌特征，导致感知身份与年龄偏差，从而欺骗人类与机器。本文提出 DiffClean，一种基于文本引导扩散模型的妆容清除方法，以抵御妆容攻击。相比带妆图像，该方法使年龄估计（未成年/成年分类）准确率提升5.8%，人脸验证在FMR=0.01时误拒率（TMR）降低5.1%。该方法对数字模拟与真实世界妆容均具有鲁棒性，在生物特征与视觉质量上优于多个基线方法。代码已开源：https://github.com/Ektagavas/DiffClean。
原文摘要 · Abstract (English)
Accurate age verification can protect underage users from unauthorized access to online platforms and e-commerce sites that provide age-restricted services. However, accurate age estimation can be confounded by several factors, including facial makeup that can induce changes to alter perceived identity and age to fool both humans and machines. In this work, we propose DiffClean which erases makeup traces using a text-guided diffusion model to defend against makeup attacks. DiffClean improves age estimation (minor vs. adult accuracy by 5.8%) and face verification (TMR by 5.1% at FMR=0.01%) compared to images with makeup. Our method is robust across digitally simulated and real-world makeup styles, and outperforms multiple baselines in terms of biometric and perceptual quality. Our codes are available at https://github.com/Ektagavas/DiffClean.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。