Blind Face Restoration
Blind face restoration aims at recovering high-quality faces from the low-quality counterparts suffering from unknown degradation, such as low-resolution, noise, blur, compression artifacts, etc. When applied to real-world scenarios, it becomes more challenging, due to more complicated degradation, diverse poses and expressions.
Description source: Towards Real-World Blind Face Restoration with Generative Facial Prior
Image source: Towards Real-World Blind Face Restoration with Generative Facial Prior
Papers
Showing 1–10 of 55 papers
Benchmark Results
| # | Model | Metric | Claimed | Verified | Status |
|---|---|---|---|---|---|
| 1 | DFDNet | LPIPS | 55.4 | — | Unverified |
| 2 | PULSE | LPIPS | 50.8 | — | Unverified |
| 3 | PSFRGAN | LPIPS | 50 | — | Unverified |
| 4 | GFPGAN | LPIPS | 49.5 | — | Unverified |
| 5 | HiFaceGAN | LPIPS | 47.7 | — | Unverified |
| 6 | VQFR | LPIPS | 47.1 | — | Unverified |
| 7 | GLEAN | LPIPS | 46.9 | — | Unverified |
| 8 | mGANprior | LPIPS | 45.84 | — | Unverified |
| 9 | DiffBIR | LPIPS | 45.73 | — | Unverified |
| 10 | DifFace | LPIPS | 43.5 | — | Unverified |