# Blind Face Restoration via Deep Multi-scale Component Dictionaries

arXiv: https://arxiv.org/abs/2008.00418 · HTML: https://mlsanity.com/paper/2008.00418/

## Key facts

- Cited by 106 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 2 Aug 2020.

## Built on by (most cited first, 30 of 106)

- [Image Super-Resolution via Iterative Refinement](https://mlsanity.com/paper/2104.07636/) (2021)
- [Towards Real-World Blind Face Restoration with Generative Facial Prior](https://mlsanity.com/paper/2101.04061/) (2021)
- [DiffBIR: Towards Blind Image Restoration with Generative Diffusion Prior](https://mlsanity.com/paper/2308.15070/) (2023)
- [Towards Robust Blind Face Restoration with Codebook Lookup Transformer](https://mlsanity.com/paper/2206.11253/) (2022)
- [GAN Prior Embedded Network for Blind Face Restoration in the Wild](https://mlsanity.com/paper/2105.06070/) (2021)
- [VFHQ: A High-Quality Dataset and Benchmark for Video Face Super-Resolution](https://mlsanity.com/paper/2205.03409/) (2022)
- [Low-Light Image and Video Enhancement Using Deep Learning: A Survey](https://mlsanity.com/paper/2104.10729/) (2021)
- [VQFR: Blind Face Restoration with Vector-Quantized Dictionary and Parallel Decoder](https://mlsanity.com/paper/2205.06803/) (2022)
- [Real-World Blind Super-Resolution via Feature Matching with Implicit High-Resolution Priors](https://mlsanity.com/paper/2202.13142/) (2022)
- [DifFace: Blind Face Restoration with Diffused Error Contraction](https://mlsanity.com/paper/2212.06512/) (2022)
- [LEDNet: Joint Low-light Enhancement and Deblurring in the Dark](https://mlsanity.com/paper/2202.03373/) (2022)
- [HifiFace: 3D Shape and Semantic Prior Guided High Fidelity Face Swapping](https://mlsanity.com/paper/2106.09965/) (2021)
- [RestoreFormer: High-Quality Blind Face Restoration from Undegraded Key-Value Pairs](https://mlsanity.com/paper/2201.06374/) (2022)
- [DR2: Diffusion-based Robust Degradation Remover for Blind Face Restoration](https://mlsanity.com/paper/2303.06885/) (2023)
- [DiffusionRig: Learning Personalized Priors for Facial Appearance Editing](https://mlsanity.com/paper/2304.06711/) (2023)
- [Efficient Diffusion Model for Image Restoration by Residual Shifting](https://mlsanity.com/paper/2403.07319/) (2024)
- [Learning Semantic-Aware Knowledge Guidance for Low-Light Image Enhancement](https://mlsanity.com/paper/2304.07039/) (2023)
- [PGDiff: Guiding Diffusion Models for Versatile Face Restoration via Partial Guidance](https://mlsanity.com/paper/2309.10810/) (2023)
- [Learning Dual Memory Dictionaries for Blind Face Restoration](https://mlsanity.com/paper/2210.08160/) (2022)
- [GCFSR: a Generative and Controllable Face Super Resolution Method Without Facial and GAN Priors](https://mlsanity.com/paper/2203.07319/) (2022)
- [RestoreFormer++: Towards Real-World Blind Face Restoration from Undegraded Key-Value Pairs](https://mlsanity.com/paper/2308.07228/) (2023)
- [OSDFace: One-Step Diffusion Model for Face Restoration](https://mlsanity.com/paper/2411.17163/) (2024)
- [Deep Learning-based Face Super-Resolution: A Survey](https://mlsanity.com/paper/2101.03749/) (2021)
- [IFQA: Interpretable Face Quality Assessment](https://mlsanity.com/paper/2211.07077/) (2022)
- [Learning Generative Structure Prior for Blind Text Image Super-resolution](https://mlsanity.com/paper/2303.14726/) (2023)
- [Dual Associated Encoder for Face Restoration](https://mlsanity.com/paper/2308.07314/) (2023)
- [Towards Real-World Blind Face Restoration with Generative Diffusion Prior](https://mlsanity.com/paper/2312.15736/) (2023)
- [LTT-GAN: Looking Through Turbulence by Inverting GANs](https://mlsanity.com/paper/2112.02379/) (2021)
- [Effective Diffusion Transformer Architecture for Image Super-Resolution](https://mlsanity.com/paper/2409.19589/) (2024)
- [GLEAN: Generative Latent Bank for Image Super-Resolution and Beyond](https://mlsanity.com/paper/2207.14812/) (2022)

## Abstract (arXiv)

Recent reference-based face restoration methods have received considerable attention due to their great capability in recovering high-frequency details on real low-quality images. However, most of these methods require a high-quality reference image of the same identity, making them only applicable in limited scenes. To address this issue, this paper suggests a deep face dictionary network (termed as DFDNet) to guide the restoration process of degraded observations. To begin with, we use K-means to generate deep dictionaries for perceptually significant face components (ie, left/right eyes, nose and mouth) from high-quality images. Next, with the degraded input, we match and select the most similar component features from their corresponding dictionaries and transfer the high-quality details to the input via the proposed dictionary feature transfer (DFT) block. In particular, component AdaIN is leveraged to eliminate the style diversity between the input and dictionary features (eg, illumination), and a confidence score is proposed to adaptively fuse the dictionary feature to the input. Finally, multi-scale dictionaries are adopted in a progressive manner to enable the coarse-to-fine restoration. Experiments show that our proposed method can achieve plausible performance in both quantitative and qualitative evaluation, and more importantly, can generate realistic and promising results on real degraded images without requiring an identity-belonging reference. The source code and models are available at urlhttps://github.com/csxmli2016/DFDNet.