VQFR (ECCV 2022 Oral)

1. Colab Demo for VQFR
2. Online demo: Replicate.ai (may need to sign in, return the whole image)

🚩 Updates

• ✅ 2022.10.16 Clean research codes & Update VQFR-v2. In this version, we emphasize the restoration quality of the texture branch and balance fidelity with user control.

• ✅ Support enhancing non-face regions (background) with Real-ESRGAN.

• ✅ The Colab Demo of VQFR is created.

• ✅ The training/inference codes and pretrained models in paper are released.

This paper aims at investigating the potential and limitation of Vector-Quantized (VQ) dictionary for blind face restoration.
We propose a new framework VQFR – incoporating the Vector-Quantized Dictionary and the Parallel Decoder. Compare with previous arts, VQFR produces more realistic facial details and keep the comparable fidelity.

---

VQFR: Blind Face Restoration with Vector-Quantized Dictionary and Parallel Decoder

[Paper]   [Project Page]   [Video]   [B站]   [Poster]   [Slides]
Yuchao Gu, Xintao Wang, Liangbin Xie, Chao Dong, Gen Li, Ying Shan, Ming-Ming Cheng
Nankai University; Tencent ARC Lab; Tencent Online Video; Shanghai AI Laboratory;
Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences

---

🔧 Dependencies and Installation

• Python >= 3.7 (Recommend to use Anaconda or Miniconda)
• PyTorch >= 1.7
• Option: NVIDIA GPU + CUDA
• Option: Linux

Installation

1. Clone repo

   git clone https://github.com/TencentARC/VQFR.git
   cd VQFR

2. Install dependent packages

   # Build VQFR with extension
   pip install -r requirements.txt
   VQFR_EXT=True python setup.py develop
   
   # Following packages are required to run demo.py
   
   # Install basicsr - https://github.com/xinntao/BasicSR
   pip install basicsr
   
   # Install facexlib - https://github.com/xinntao/facexlib
   # We use face detection and face restoration helper in the facexlib package
   pip install facexlib
   
   # If you want to enhance the background (non-face) regions with Real-ESRGAN,
   # you also need to install the realesrgan package
   pip install realesrgan

⚡ Quick Inference

Download pre-trained VQFRv1/v2 models [Google Drive].

Inference

# for real-world image
python demo.py -i inputs/whole_imgs -o results -v 2.0 -s 2 -f 0.1

# for cropped face
python demo.py -i inputs/cropped_faces/ -o results -v 2.0 -s 1 -f 0.1 --aligned

Usage: python demo.py -i inputs/whole_imgs -o results -v 2.0 -s 2 -f 0.1 [options]...

  -h                   show this help
  -i input             Input image or folder. Default: inputs/whole_imgs
  -o output            Output folder. Default: results
  -v version           VQFR model version. Option: 1.0. Default: 1.0
  -f fidelity_ratio    VQFRv2 model supports user control fidelity ratio, range from [0,1]. 0 for the best quality and 1 for the best fidelity. Default: 0
  -s upscale           The final upsampling scale of the image. Default: 2
  -bg_upsampler        background upsampler. Default: realesrgan
  -bg_tile             Tile size for background sampler, 0 for no tile during testing. Default: 400
  -suffix              Suffix of the restored faces
  -only_center_face    Only restore the center face
  -aligned             Input are aligned faces
  -ext                 Image extension. Options: auto | jpg | png, auto means using the same extension as inputs. Default: auto

💻 Training

We provide the training codes for VQFR (used in our paper).

• Dataset preparation: FFHQ
• Download lpips weights [Google Drive] into experiments/pretrained_models/

Codebook Training

• Pre-train VQ codebook on FFHQ datasets.

 python -m torch.distributed.launch --nproc_per_node=8 --master_port=2022 vqfr/train.py -opt options/train/VQGAN/train_vqgan_v1_B16_800K.yml --launcher pytorch

• Or download our pretrained VQ codebook Google Drive and put them in the experiments/pretrained_models folder.

Restoration Training

• Modify the configuration file options/train/VQFR/train_vqfr_v1_B16_200K.yml accordingly.

• Training

python -m torch.distributed.launch --nproc_per_node=8 --master_port=2022 vqfr/train.py -opt options/train/VQFR/train_vqfr_v1_B16_200K.yml --launcher pytorch

📏 Evaluation

We evaluate VQFR on one synthetic dataset CelebA-Test, and three real-world datasets LFW-Test, CelebChild and Webphoto-Test. For reproduce our evaluation results, you need to perform the following steps:

1. Download testing datasets (or VQFR results) by the following links:

Name	Datasets	Short Description	Download	VQFR Results
Testing Datasets	CelebA-Test(LQ/HQ)	3000 (LQ, HQ) synthetic images for testing	Google Drive	Google Drive
	LFW-Test(LQ)	1711 real-world images for testing
	CelebChild(LQ)	180 real-world images for testing
	Webphoto-Test(LQ)	469 real-world images for testing

2. Install related package and download pretrained models for different metrics:

    # LPIPS
    pip install lpips

    # Deg.
    cd metric_paper/
    git clone https://github.com/ronghuaiyang/arcface-pytorch.git
    mv arcface-pytorch/ arcface/
    rm arcface/config/__init__.py arcface/models/__init__.py

    # put pretrained models of different metrics to "experiments/pretrained_models/metric_weights/"

Metrics	Pretrained Weights	Download
FID	inception_FFHQ_512.pth	Google Drive
Deg	resnet18_110.pth
LMD	alignment_WFLW_4HG.pth

3. Generate restoration results:

• Specify the dataset_lq/dataset_gt to the testing dataset root in test_vqfr_v1.yml.

• Then run the following command:

    python vqfr/test.py -opt options/test/VQFR/test_vqfr_v1.yml

4. Run evaluation:

    # LPIPS|PSNR/SSIM|LMD|Deg.
    python metric_paper/[calculate_lpips.py|calculate_psnr_ssim.py|calculate_landmark_distance.py|calculate_cos_dist.py]
    -restored_folder folder_to_results -gt_folder folder_to_gt

    # FID|NIQE
    python metric_paper/[calculate_fid_folder.py|calculate_niqe.py] -restored_folder folder_to_results

📜 License

VQFR is released under Apache License Version 2.0.

👀 Acknowledgement

Thanks to the following open-source projects:

Taming-transformers

GFPGAN

DistSup

📋 Citation

@inproceedings{gu2022vqfr,
  title={VQFR: Blind Face Restoration with Vector-Quantized Dictionary and Parallel Decoder},
  author={Gu, Yuchao and Wang, Xintao and Xie, Liangbin and Dong, Chao and Li, Gen and Shan, Ying and Cheng, Ming-Ming},
  year={2022},
  booktitle={ECCV}
}

📧 Contact

If you have any question, please email yuchaogu9710@gmail.com.