Unveiling the real appearance of retouched faces to prevent malicious users from deceptive advertising and economic fraud has been an increasing concern in the era of digital economics. This article makes the first attempt to investigate the face retouching reversal (FRR) problem. We first collect an FRR dataset, named deepFRR, which contains 50,000 StyleGAN-generated high-resolution (1024*1024) facial images and their corresponding retouched ones by a commercial online API. To our best knowledge, deepFRR is the first FRR dataset tailored for training the deep FRR models. Then, we propose a novel diffusion-based FRR approach (FRRffusion) for the FRR task. Our FRRffusion consists of a coarse-to-fine two-stage network: A diffusion-based Facial Morpho-Architectonic Restorer (FMAR) is constructed to generate the basic contours of low-resolution faces in the first stage, while a Transformer-based Hyperrealistic Facial Detail Generator (HFDG) is designed to create high-resolution facial details in the second stage. Tested on deepFRR, our FRRffusion surpasses the GP-UNIT and Stable Diffusion methods by a large margin in four widespread quantitative metrics. Especially, the de-retouched images by our FRRffusion are visually much closer to the raw face images than both the retouched face images and those restored by the GP-UNIT and Stable Diffusion methods in terms of qualitative evaluation with 85 subjects. These results sufficiently validate the efficacy of our work, bridging the recently-standing gap between the FRR and generic image restoration tasks. The dataset and code are available at https://github.com/GZHU-DVL/FRRffusion.

翻译：在数字经济学时代，揭示修饰后面部的真实外观以防止恶意用户进行欺骗性广告和经济欺诈日益受到关注。本文首次对面部修饰逆转（FRR）问题展开研究。我们首先收集了一个名为deepFRR的FRR数据集，该数据集包含50,000张由StyleGAN生成的高分辨率（1024*1024）人脸图像及其对应的商用在线API修饰版本。据我们所知，deepFRR是首个专门用于训练深度FRR模型的数据集。随后，我们提出了一种新颖的基于扩散的FRR方法（FRRffusion）以解决FRR任务。FRRffusion包含一个由粗到精的两阶段网络：第一阶段构建基于扩散的面部形态架构恢复器（FMAR）以生成低分辨率人脸的基本轮廓，第二阶段设计基于Transformer的超真实面部细节生成器（HFDG）以创建高分辨率面部细节。在deepFRR上的测试表明，FRRffusion在四个广泛使用的量化指标上大幅超越GP-UNIT和Stable Diffusion方法。特别地，在包含85名受试者的定性评估中，FRRffusion得到的去修饰图像在视觉效果上比修饰后面部图像以及GP-UNIT和Stable Diffusion方法恢复的图像更接近原始人脸图像。这些结果充分验证了我们方法的有效性，弥合了近期FRR与通用图像恢复任务之间的差距。数据集和代码已在https://github.com/GZHU-DVL/FRRffusion公开。