A curated list of awesome face restoration & enhancement papers and resources 🐳, inspired by awesome-NeRF.
Welcome to add papers and other resources related to this topic [submit a pull request] 🤗
[CVPR 2023]DR2: Diffusion-based Robust Degradation Remover for Blind Face Restoration, Wang et al. Paper | Bibtex[Arxiv 2022]DifFace: Blind Face Restoration with Diffused Error Contraction, Yue et al. Paper | Github | Demo | Bibtex
-
[NeurIPS 2022]CodeFormer: Towards Robust Blind Face Restoration with Codebook Lookup Transformer, Zhou et al. Paper | Project | Github | Demo | Bibtex -
[ECCV 2022]VQFR: Blind Face Restoration with Vector-Quantized Dictionary and Parallel Decoder, Gu et al. Paper | Project | Github | Bibtex -
[CVPR 2022]RestoreFormer: High-Quality Blind Face Restoration from Undegraded Key-Value Pairs, Wang et al. Paper | Github | Bibtex -
[CVPR 2022]Rethinking Deep Face Restoration. Zhao et al. Paper | Bibtex
-
[CVPR 2021]GFPGAN: Towards Real-World Blind Face Restoration with Generative Facial Prior, Wang et al. Paper | Project | Github | Demo | Bibtex -
[CVPR 2021]GLEAN: Generative Latent Bank for Large-Factor Image Super-Resolution, Chan et al. Paper | Project | Github | Bibtex -
[CVPR 2021]GPEN: GAN Prior Embedded Network for Blind Face Restoration in the Wild, Yang et al. Paper | Github | Bibtex
[CVPR 2020]PULSE: Self-Supervised Photo Upsampling via Latent Space Exploration of Generative Models, Menon et al. Paper | Github | Bibtex
[TPAMI 2022]DMDNet: Learning Dual Memory Dictionaries for Blind Face Restoration, Li et al. Paper | Github | CelebRef-HQ Dataset | Bibtex[ECCV 2020]DFDNet: Blind Face Restoration via Deep Multi-scale Component Dictionaries, Li et al. Paper | Github | Bibtex
[CVPR 2020]ASFFNet: Enhanced Blind Face Restoration With Multi-Exemplar Images and Adaptive Spatial Feature Fusion, Li et al. Paper | Github | Bibtex
[CVPR 2021]PSFRGAN: Progressive Semantic-Aware Style Transformation for Blind Face Restoration, Chen et al. Paper | Github | Bibtex
[CVPR 2022]SGPN: Blind Face Restoration via Integrating Face Shape and Generative Priors, Zhu et al. Paper | Bibtex
[ArXiv 2022]MyStyle: A Personalized Generative Prior, Nitzan et al. Paper | Github | Project | Bibtex
[TIP 2020]Learning Spatial Attention for Face Super-Resolution, Chen et al. Paper | Github | Bibtex
[CVPRW 2022]VFHQ: A High-Quality Dataset and Benchmark for Video Face Super-Resolution, Xie et al. Paper | Project | Bibtex
| Dataset | Resolution | Description |
|---|---|---|
| FFHQ | 1024 x 1024 | 7,0000 high-quality face images (usually used for training) |
| CelebA-HQ | 1024 x 1024 | 3,0000 high-quality face images (usually used for evaluation) |
| CelebAMask-HQ | 512 x 512 | 3,0000 face images with 19 facial classes |
| CelebRef-HQ | 512 x 512 | high-quality face images with multiple same-identity references |
| Dataset | Description |
|---|---|
| CelebA | a large-scale face attributes dataset with more than 200K celebrity images |
| WIDER-Test | 970 real-world severely degraded face images from the WIDER Face dataset (for test) |
| LFW-Test | 1711 real-world degraded faces collected from the LFW dataset (for test) |
| WebPhoto-Test | 407 real-world degraded faces collected from the Internet (for test) |
| CelebChild-Test | 180 real-world degraded child faces collected from the Internet (for test) |
| Dataset | Description |
|---|---|
| TalkingHead-1KH | 500k video clips, of which about 80k are greater than 512x512 resolution |
| VFHQ | 16,000 high-fidelity clips of diverse interview scenarios |
| CelebV-HQ | 35,666 video clips involving 15,653 identities and 83 manually labeled facial attributes |
| CelebV-Text | 70,000 in-the-wild face video clips covering diverse visual content |
| Dataset | Description |
|---|---|
| CelebA-Dialog | a large-scale visual-language face dataset with fine-grained labels and captions |
| CelebA-Spoof | a large-scale face anti-spoofing dataset with rich attributes and spoof types |
| PPR10K | a large-scale portrait photo retouching dataset |