# MoFRR: Mixture of Diffusion Models for Face Retouching Restoration

arXiv: https://arxiv.org/abs/2507.19770 · HTML: https://mlsanity.com/paper/2507.19770/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Placed in Inverse problems and image restoration, one of 14 directions in Diffusion models.
- Builds on 21 of its 46 references that are in the map.
- First posted on arXiv 26 Jul 2025.

## Placed in

- Diffusion models / [Inverse problems and image restoration](https://mlsanity.com/diffusion/inverse-problems-and-image-restoration/)

## Builds on (most cited first, 21 of 21)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Denoising Diffusion Implicit Models](https://mlsanity.com/paper/2010.02502/) (2020)
- [A Style-Based Generator Architecture for Generative Adversarial Networks](https://mlsanity.com/paper/1812.04948/) (2018)
- [Image-to-Image Translation with Conditional Adversarial Networks](https://mlsanity.com/paper/1611.07004/) (2016)
- [Restormer: Efficient Transformer for High-Resolution Image Restoration](https://mlsanity.com/paper/2111.09881/) (2021)
- [AdaFace: Quality Adaptive Margin for Face Recognition](https://mlsanity.com/paper/2204.00964/) (2022)
- [One-Step Effective Diffusion Network for Real-World Image Super-Resolution](https://mlsanity.com/paper/2406.08177/) (2024)
- [VQFR: Blind Face Restoration with Vector-Quantized Dictionary and Parallel Decoder](https://mlsanity.com/paper/2205.06803/) (2022)
- [Attentional Feature Fusion](https://mlsanity.com/paper/2009.14082/) (2020)
- [Blind Face Restoration via Deep Multi-scale Component Dictionaries](https://mlsanity.com/paper/2008.00418/) (2020)
- [DR2: Diffusion-based Robust Degradation Remover for Blind Face Restoration](https://mlsanity.com/paper/2303.06885/) (2023)
- [LADN: Local Adversarial Disentangling Network for Facial Makeup and De-Makeup](https://mlsanity.com/paper/1904.11272/) (2019)
- [ResDiff: Combining CNN and Diffusion Model for Image Super-Resolution](https://mlsanity.com/paper/2303.08714/) (2023)
- [RestoreFormer++: Towards Real-World Blind Face Restoration from Undegraded Key-Value Pairs](https://mlsanity.com/paper/2308.07228/) (2023)
- [SSAT: A Symmetric Semantic-Aware Transformer Network for Makeup Transfer and Removal](https://mlsanity.com/paper/2112.03631/) (2021)
- [PSGAN++: Robust Detail-Preserving Makeup Transfer and Removal](https://mlsanity.com/paper/2105.12324/) (2021)
- [Content-Style Decoupling for Unsupervised Makeup Transfer without Generating Pseudo Ground Truth](https://mlsanity.com/paper/2405.17240/) (2024)
- [RetouchingFFHQ: A Large-scale Dataset for Fine-grained Face Retouching Detection](https://mlsanity.com/paper/2307.10642/) (2023)

## Built on by (most cited first, 4 of 4)

- [RetouchIQ: MLLM Agents for Instruction-Based Image Retouching with Generalist Reward](https://mlsanity.com/paper/2602.17558/) (2026)
- [BeautyGRPO: Aesthetic Alignment for Face Retouching via Dynamic Path Guidance and Fine-Grained Preference Modeling](https://mlsanity.com/paper/2603.01163/) (2026)
- [MirrorPPR: Exemplar-Based Portrait Photo Retouching](https://mlsanity.com/paper/2606.29308/) (2026)
- [FlowTool: Controlling Tool Parameter in Image Retouching via Flow Matching](https://mlsanity.com/paper/2609.35673/) (2026)

## Abstract (arXiv)

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.