Research map / Image generation / Image restoration
MoFRR: Mixture of Diffusion Models for Face Retouching Restoration
Jiaxin Liu, Qichao Ying, Zhenxing Qian, Sheng Li, Runqi Zhang, Jian Liu, Xinpeng Zhang
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add IDEM module (ablation) | WaveFRR/MoFRR · RetouchingFFHQ++ intra-API ablation (Single) | PSNR: 34.34 -> 36.12 | Improved |
| add IDEM module (ablation) | WaveFRR/MoFRR · RetouchingFFHQ++ intra-API ablation (Multi) | PSNR: 32.94 -> 34.47 | Improved |
| add Degree Estimator (ablation) | MoFRR · RetouchingFFHQ++ intra-API ablation (Single) | PSNR: 34.43 -> 36.12 | Improved |
| add HFCAM high-frequency module (ablation) | MoFRR · RetouchingFFHQ++ intra-API ablation (Single) | PSNR: 34.69 -> 36.12 | Improved |
| add HFCAM high-frequency module (ablation) | MoFRR · RetouchingFFHQ++ intra-API ablation (Multi) | PSNR: 33.04 -> 34.47 | Improved |
| add shared expert (ablation) | MoFRR · RetouchingFFHQ++ intra-API ablation (Multi) | PSNR: 32.42 -> 34.47 | Improved |
| add shared expert (ablation) | MoFRR · RetouchingFFHQ++ intra-API ablation (Single) | PSNR: 35.37 -> 36.12 | Improved |
| add router to select experts (ablation) | MoFRR · RetouchingFFHQ++ intra-API ablation (Multi) | PSNR: 34.19 -> 34.47 | No clear effect |
| add router to select experts (ablation) | MoFRR · RetouchingFFHQ++ intra-API ablation (Single) | PSNR: 35.63 -> 36.12 | No clear effect |
| use mixture of experts instead of a single WaveFRR (ablation) | MoFRR · RetouchingFFHQ++ intra-API ablation (Multi) | PSNR: 31.09 -> 34.47 | Improved |
| use mixture of experts instead of a single WaveFRR (ablation) | MoFRR · RetouchingFFHQ++ intra-API ablation (Single) | PSNR: 35.18 -> 36.12 | Improved |
| train on other APIs and test on Portrait (cross-API) vs best baseline | MoFRR · RetouchingFFHQ++ cross-API (Multi) | PSNR: 26.79 -> 31.28 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.
- ResDiff — ResDiff: Combining CNN and Diffusion Model for Image Super-resolution (AAAI 2024) · better on 8 of 8 shared results
- Restormer — Restormer: Efficient Transformer for High-Resolution Image Restoration (CVPR 2022) · better on 8 of 8 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- OSDFace: One-Step Diffusion Model for Face Restoration (CVPR 2025 · similarity 0.88)
- Overcoming False Illusions in Real-World Face Restoration with Multi-Modal Guided Diffusion Model (ICLR 2025 · similarity 0.88)
- RetouchFormer: Semi-supervised High-Quality Face Retouching Transformer with Prior-Based Selective Self-Attention (AAAI 2024 · similarity 0.87)
- DiffRetouch: Using Diffusion to Retouch on the Shoulder of Experts (AAAI 2025 · similarity 0.87)
- PFStorer: Personalized Face Restoration and Super-Resolution (CVPR 2024 · similarity 0.87)
- Self-Supervised Selective-Guided Diffusion Model for Old-Photo Face Restoration (NeurIPS 2025 · similarity 0.87)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
