FRRffusion：通过基于扩散的人脸修图逆转揭示真实面貌
FRRffusion: Unveiling Authenticity with Diffusion-Based Face Retouching Reversal
AI总结：
针对人脸修图逆转需求，本文构建首个专用深度训练数据集deepFRR，提出两阶段扩散模型FRRffusion，在量化指标和主观评估上均优于现有方法，填补了相关任务空白。
摘要：
在数字经济时代，还原被修图人脸的真实面貌以防止恶意用户进行虚假广告和经济欺诈已日益受到关注。本文首次尝试研究人脸修图逆转（Face Retouching Reversal，FRR）问题。我们首先收集了一个名为deepFRR的FRR数据集，其中包含50000张由StyleGAN生成的高分辨率（1024*1024）人脸图像，以及通过商业在线API生成的对应修图版本。据我们所知，deepFRR是首个专为训练深度FRR模型打造的FRR数据集。随后，我们提出了一种新颖的基于扩散的FRR方法（FRRffusion）用于完成FRR任务。我们的FRRffusion由一个由粗到精的两阶段网络构成：第一阶段构建了基于扩散的人脸形态结构修复器（Facial Morpho-Architectonic Restorer，FMAR），用于生成低分辨率人脸的基本轮廓；第二阶段设计了基于Transformer的超写实人脸细节生成器（Hyperrealistic Facial Detail Generator，HFDG），用于生成高分辨率人脸细节。在deepFRR上测试表明，我们的FRRffusion在四项常用量化指标上大幅优于GP-UNIT和Stable Diffusion方法。特别是在85名受试者参与的定性评估中，我们的FRRffusion生成的去修图图像在视觉上比修图人脸图像、以及GP-UNIT和Stable Diffusion方法修复的图像都更接近原始人脸图像。这些结果充分验证了我们工作的有效性，填补了当前FRR与通用图像修复任务之间存在的空白。数据集和代码可在https://github.com/GZHU-DVL/FRRffusion获取。
英文摘要：
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.
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。
