Blind face restoration usually relies on facial priors, such as facial geometry prior or reference prior, to restore realistic and faithful details. However, very low-quality inputs cannot offer accurate geometric prior while high-quality references are inaccessible, limiting the applicability in real-world scenarios. In this work, we propose GFP-GAN that leverages
rich and diverse priors encapsulated in a pretrained face GAN
for blind face restoration. This Generative Facial Prior (GFP) is incorporated into the face restoration process via novel channel-split spatial feature transform layers, which allow our method to achieve a good balance of realness and fidelity. Thanks to the powerful generative facial prior and delicate designs, our GFP-GAN could jointly restore facial details and enhance colors with just a single forward pass, while GAN inversion methods require expensive image-specific optimization at inference. Extensive experiments show that our method achieves superior performance to prior art on both synthetic and real-world datasets.
BibTeX
@InProceedings{wang2021gfpgan,
author = {Xintao Wang and Yu Li and Honglun Zhang and Ying Shan},
title = {Towards Real-World Blind Face Restoration with Generative Facial Prior},
booktitle={The IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
year = {2021}
}
git clone https://github.com/xinntao/GFPGAN.git
cd GFPGAN
Install dependent packages
# Install basicsr - https://github.com/xinntao/BasicSR# We use BasicSR for both training and inference# Set BASICSR_EXT=True to compile the cuda extensions in the BasicSR - It may take several minutes to compile, please be patient
BASICSR_EXT=True 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
pip install -r requirements.txt
GFPGAN is realeased under Apache License Version 2.0.
:e-mail: Contact
If you have any question, please email
xintao.wang@outlook.com
or
xintaowang@tencent.com
.
Runs of TencentARC GFPGANv1 on huggingface.co
0
Total runs
0
24-hour runs
0
3-day runs
0
7-day runs
0
30-day runs
More Information About GFPGANv1 huggingface.co Model
GFPGANv1 huggingface.co
GFPGANv1 huggingface.co is an AI model on huggingface.co that provides GFPGANv1's model effect (), which can be used instantly with this TencentARC GFPGANv1 model. huggingface.co supports a free trial of the GFPGANv1 model, and also provides paid use of the GFPGANv1. Support call GFPGANv1 model through api, including Node.js, Python, http.
GFPGANv1 huggingface.co is an online trial and call api platform, which integrates GFPGANv1's modeling effects, including api services, and provides a free online trial of GFPGANv1, you can try GFPGANv1 online for free by clicking the link below.
TencentARC GFPGANv1 online free url in huggingface.co:
GFPGANv1 is an open source model from GitHub that offers a free installation service, and any user can find GFPGANv1 on GitHub to install. At the same time, huggingface.co provides the effect of GFPGANv1 install, users can directly use GFPGANv1 installed effect in huggingface.co for debugging and trial. It also supports api for free installation.