用混合扩散模型还原被美颜修饰的脸，恢复原貌细节。
MoFRR: Mixture of Diffusion Models for Face Retouching Restoration
- 分专家处理不同美颜类型，共享专家应对通用痕迹。
- 低频修复由迭代失真评估引导，高频细节通过交叉注意力优化。
- 在新构建的数据集上表现优异，适合图像真实性研究者。
社交媒体上广泛使用的面部美颜功能引发了图像真实性的担忧。现有方法多聚焦于检测美颜痕迹，但如何从美颜后的图像中准确恢复原始人脸仍无解决方案。本文提出人脸美颜修复（FRR）这一新任务，旨在还原被修饰的人脸。与传统图像修复不同，FRR需应对多种类型和程度的复杂修饰，重点在于低频信息的恢复。为此，我们提出MoFRR：基于扩散模型的混合架构。受DeepSeek专家隔离策略启发，MoFRR采用稀疏激活机制，由专门处理特定美颜类型的专家和一个处理通用美颜痕迹的共享专家组成。每个专用专家采用双分支结构：基于DDIM的低频分支由迭代失真评估模块（IDEM）引导，交叉注意力高频频分支（HFCAM）用于细节精修。在新构建的美颜数据集RetouchingFFHQ++上的大量实验表明，MoFRR在FRR任务中表现卓越。
原文摘要 · Abstract (English)
The widespread use of face retouching on social media platforms raises concerns about the authenticity of face images. While existing methods focus on detecting face retouching, how to accurately recover the original faces from the retouched ones has yet to be answered. This paper introduces Face Retouching Restoration (FRR), a novel computer vision task aimed at restoring original faces from their retouched counterparts. FRR differs from traditional image restoration tasks by addressing the complex retouching operations with various types and degrees, which focuses more on the restoration of the low-frequency information of the faces. To tackle this challenge, we propose MoFRR, Mixture of Diffusion Models for FRR. Inspired by DeepSeek's expert isolation strategy, the MoFRR uses sparse activation of specialized experts handling distinct retouching types and the engagement of a shared expert dealing with universal retouching traces. Each specialized expert follows a dual-branch structure with a DDIM-based low-frequency branch guided by an Iterative Distortion Evaluation Module (IDEM) and a Cross-Attention-based High-Frequency branch (HFCAM) for detail refinement. Extensive experiments on a newly constructed face retouching dataset, RetouchingFFHQ++, demonstrate the effectiveness of MoFRR for FRR.
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。