https://github.com/HDCVLab/EDFace-Celeb-1M

https://github.com/HDCVLab/EDFace-Celeb-1M

Last synced: 29 days ago
JSON representation

• Host: GitHub
• URL: https://github.com/HDCVLab/EDFace-Celeb-1M
• Owner: HDCVLab
• Created: 2021-10-10T23:49:34.000Z (about 3 years ago)
• Default Branch: main
• Last Pushed: 2024-08-12T23:35:22.000Z (4 months ago)
• Last Synced: 2024-08-13T02:02:55.327Z (4 months ago)
• Size: 55.7 KB
• Stars: 97
• Watchers: 6
• Forks: 4
• Open Issues: 1
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

• Awesome-Face-Restoration - EDFace-Celeb

README

        


# EDFace-Celeb-1M: Benchmarking Face Hallucination with a Million-scale Dataset (TPAMI2022)

## Homepage

**We add the homepage of our dataset, you can visit [here](https://zhangkaihao.github.io/projects/EDface/).**

## License

The EDFace-Celeb dataset is released under [CC BY-NC-ND](https://creativecommons.org/licenses/by-nc-nd/4.0/) license.

## Our propsoed EDFace-Celeb-1M Dataset

We construct a large-scale dataset for face analysis. It consists of three sub-datasets, i.e., EDFace-Celeb-1M, EDFace-Celeb-150K and EDFace-Celeb-Real datasets. The EDFace-Celeb-1M and EDFace-Celeb-150K datasets provide different settings for face super-resolution (FH128, FH512), face hallucination (FH128, FH512) and blind face restoration (BFR128, BFR512).

****

## EDFace-Celeb-Real: Real-world low-resolution face images.

#### Download

- [Google Drive](https://drive.google.com/file/d/1FSnuDTMiF2Cossa-TQQPy2PDoiuPm8Mi/view?usp=sharing) (Unavailable)

- [Baidu Cloud](https://pan.baidu.com/s/1pmBOSKugliwgruNGrIXHhQ?pwd=sw6b)

## EDFace-Celeb-1M (FH128): Face Hallucination (HR, LR: X2, X4, X4_BD, X4_DN, X8)

#### Download

- [Google Drive](https://drive.google.com/drive/folders/1-WdxQHHjKbNvRZkE6ZJ4lNSKzz5Xt-TD?usp=sharing) (Unavailable)

- [Baidu Cloud](https://pan.baidu.com/s/190rUPBbuDYo9sfa5sovAkA?pwd=dl9g)

#### Citation:

- [EDFace-Celeb-1M: Benchmarking Face Hallucination with a Million-scale Dataset (TPAMI2022)](https://arxiv.org/abs/2110.05031)

#### Benchmarking Results (X2, X4, X4_BD, X4_DN, X8)

- [DIC](https://github.com/Maclory/Deep-Iterative-Collaboration): [Results](https://drive.google.com/drive/folders/12K6V16MXz9Qupuh44cua-2scrAxM1GWV?usp=sharing)

- [DIC-GAN](https://github.com/Maclory/Deep-Iterative-Collaboration): [Results](https://drive.google.com/drive/folders/1x827RaupFu3TJ2XcGZQTWL9Cb0lMMIaT?usp=sharing)

- [HiFaceGAN](https://github.com/Lotayou/Face-Renovation): [Results](https://drive.google.com/drive/folders/171ea1cR9zpPqVYZKlbfe4VvxPdgfALtC?usp=sharing)

- [Wavelet](https://github.com/hhb072/WaveletSRNet): [Results](https://drive.google.com/drive/folders/18wkbvIXwoNZZGYChkDmIFg5J8ObLF4v4?usp=sharing)

- [EDSR](https://github.com/sanghyun-son/EDSR-PyTorch): [Results](https://drive.google.com/drive/folders/1_663t2DSEoWZHFqEWIPu2fjUKNs0o9N5?usp=sharing)

- [RCAN](https://github.com/yulunzhang/RCAN): [Results](https://drive.google.com/drive/folders/1CAkw8qQUOkINErAkBog9VwJoaOPdtQJy?usp=sharing)

- [RDN](https://github.com/yulunzhang/RDN): [Results](https://drive.google.com/drive/folders/1tvBcOqbxnVeeTpI966eKy0LQcDd8xpz_?usp=sharing)

- [HAN](https://github.com/wwlCape/HAN): [Results](https://drive.google.com/drive/folders/1z4iOr2X0PLjEVz9ru7RxXbD7qXSFz1lN?usp=sharing)

## EDFace-Celeb-150K (FH512) : Face Hallucination (HR, LR: X2, X4, X4_BD, X4_DN, X8)

#### Download

- [Google Drive](https://drive.google.com/drive/folders/1YELx5WtV-A1i8WSVrWhKLzi78KQ7tlty?usp=sharingg) (Unavailable)

- [Baidu Cloud](https://pan.baidu.com/s/1eMz69rsnUH6FisHdAfm9vw?pwd=4nqj) 

#### Citation:

- [EDFace-Celeb-1M: Benchmarking Face Hallucination with a Million-scale Dataset (TPAMI2022)](https://arxiv.org/abs/2110.05031)

****

## EDFace-Celeb-1M (BFR128) : Blind Face Restoration (HQ, LQ: Blur, JPEG artifact, Noise, SR, Full, Full_X2, Full_X4, Full_X8)

#### Download

- [Google Drive](https://drive.google.com/drive/folders/1lrm3JZylPpVn9CBMae8HDe_HFQ8O_6E4?usp=sharing) (Unavailable)

- [Baidu Cloud](https://pan.baidu.com/s/154OSXc1iSZj9dew01USy-w?pwd=7cd1) 

#### Citation:

- [EDFace-Celeb-1M: Benchmarking Face Hallucination with a Million-scale Dataset (TPAMI2022)](https://arxiv.org/abs/2110.05031)

- [Blind Face Restoration: Benchmark Datasets and a Baseline Model](https://arxiv.org/abs/2206.03697)

## EDFace-Celeb-150K (BFR512): Blind Face Restoration (HQ, LQ: Blur, JPEG artifact, Noise, SR, Full, Full_X2, Full_X4, Full_X8)

#### Download

- [Google Drive](https://drive.google.com/drive/folders/1B3pba2rKUsyoppHOCMx0vmpNuSafKwj3?usp=sharing) (Unavailable)

- [Baidu Cloud](https://pan.baidu.com/s/1HwBvJh1WTpVvXa-fABtWGg?pwd=ovbs)

#### Citation:

- [EDFace-Celeb-1M: Benchmarking Face Hallucination with a Million-scale Dataset (TPAMI2022)](https://arxiv.org/abs/2110.05031)

- [Blind Face Restoration: Benchmark Datasets and a Baseline Model](https://arxiv.org/abs/2206.03697)

****

## Citation

If you think the EDFace-Celeb dataset is useful for your research, please cite the following paper.

```

@inproceedings{zhang2022edface,

  title={EDFace-Celeb-1M: Benchmarking Face Hallucination with a Million-scale Dataset},

  author={Zhang, Kaihao and Li, Dongxu and Luo, Wenhan and Liu, Jingyu and Deng, Jiankang and Liu, Wei and Stefanos Zafeiriou},

  booktitle={IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI)},

  year={2022}

}

```