DicFace

[ICCV2025 Highlight] DicFace: Dirichlet-Constrained Variational Codebook Learning for Temporally Coherent Video Face Restoration

Generate Convert Improve

Install / Use

/learn @fudan-generative-vision/DicFace

About this skill

Quality Score

0/100

README

<h1 align='center'>DicFace: Dirichlet-Constrained Variational Codebook Learning for Temporally Coherent Video Face Restoration</h1> <div align='center'> <a href='' target='_blank'>Yan Chen</a><sup>1*</sup>&emsp; <a href='' target='_blank'>Hanlin Shang</a><sup>1*</sup>&emsp; <a href='' target='_blank'>Ce Liu</a><sup>1</sup>&emsp; <a href='' target='_blank'>Yuxuan Chen</a><sup>1</sup>&emsp; <a href='' target='_blank'>Hui Li</a><sup>1</sup>&emsp; <a href='' target='_blank'>Weihao Yuan</a><sup>2</sup>&emsp; </div> <div align='center'> <a href='' target='_blank'>Hao Zhu</a><sup>3</sup>&emsp; <a href='' target='_blank'>Zilong Dong</a><sup>2</sup>&emsp; <a href='https://sites.google.com/site/zhusiyucs/home' target='_blank'>Siyu Zhu</a><sup>1✉️</sup>&emsp; </div> <div align='center'> <sup>1</sup>Fudan University&emsp; <sup>2</sup>Alibaba Group&emsp; <sup>3</sup>Nanjing University&emsp; </div> <div align='Center'> <i><strong><a href='https://iccv.thecvf.com/Conferences/2025' target='_blank'>ICCV 2025 Highlight</a></strong></i> </div> <br> <div align='center'> <a href='https://github.com/fudan-generative-vision/DicFace'><img src='https://img.shields.io/github/stars/fudan-generative-vision/DicFace'></a>  <a href='https://arxiv.org/abs/2506.13355'><img src='https://img.shields.io/badge/Paper-Arxiv-red'></a>   </div> <br> <table align="center" border="0" style="width: 100%; margin-top: 80px;"> <tr> <td style="text-align: center;"> <video src="https://github.com/user-attachments/assets/274ecc2b-3d89-4d31-bb0a-a5f3611fae8a" muted autoplay loop style="display: block; margin: 0 auto;"></video> </td> </tr> </table>

🖼️ Showcase

Blind Face Restoration

Face Inpainting

Face Colorization

🐾 Wild Data Examples

📰 News

2025/07/25: 🎉🎉🎉 Our paper has been accepted to ICCV 2025and selected as a highlight.
2025/06/26: 🎉🎉🎉 Our paper has been accepted to ICCV 2025.
2025/06/25: Release our test data on huggingface repo.
2025/06/23: Release our pretrained model on huggingface repo.
2025/06/17: Paper submitted on Arixiv. paper
2025/06/16: 🎉🎉🎉 Release inference scripts

📅️ Roadmap

| Status | Milestone | ETA | | :----: | :----------------------------------------------------------------------------------------------------- | :--------: | | ✅ | Inference Code release | 2025-6-16 | | ✅ | Model Weight release， baidu-link |2025-6-16 | | ✅ | Paper submitted on Arixiv | 2025-6-17 | | ✅ | Test data release | 2025-6-25 | | ✅ | Training Code release | 2025-6-26 |

⚙️ Installation

System requirement: PyTorch version >=2.4.1, python == 3.10
Tested on GPUs: A800, python version == 3.10, PyTorch version == 2.4.1, cuda version == 12.1

Download the codes:

  git clone https://github.com/fudan-generative-vision/DicFace
  cd DicFace

Create conda environment:

  conda create -n DicFace python=3.10
  conda activate DicFace

Install PyTorch

  conda install pytorch==2.4.1 torchvision==0.19.1 torchaudio==2.4.1 pytorch-cuda=12.1 -c pytorch -c nvidia

Install packages with pip

  pip install -r requirements.txt
  python basicsr/setup.py develop
  conda install -c conda-forge dlib

📥 Download Pretrained Models

The pre-trained weights have been uploaded to Baidu Netdisk. Please download them from the link

Now you can easily get all pretrained models required by inference from our HuggingFace repo.

File Structure of Pretrained Models The downloaded .ckpts directory contains the following pre-trained models:

.ckpts
|-- CodeFormer                  # CodeFormer-related models
|   |-- bfr_100k.pth            # Blind Face Restoration model 
|   |-- color_100k.pth          # Color Restoration model 
|   |-- codeformer.pth          # codeformer model
|   |-- vqgan_discriminator.pth # vqgan_discriminator model
|   `-- inpainting_100k.pth     # Image Inpainting model
|-- dlib                        # dlib face-related models
|   |-- mmod_human_face_detector.dat  # Human face detector
|   `-- shape_predictor_5_face_landmarks.dat  # 5-point face landmark predictor
|-- facelib                     # Face processing library models
|   |-- detection_Resnet50_Final.pth  # ResNet50 face detector 
|   |-- detection_mobilenet0.25_Final.pth  # MobileNet0.25 face detector 
|   |-- parsing_parsenet.pth    # Face parsing model
|   |-- yolov5l-face.pth        # YOLOv5l face detection model
|   `-- yolov5n-face.pth        # YOLOv5n face detection model
|-- realesrgan                  # Real-ESRGAN super-resolution model
|   `-- RealESRGAN_x2plus.pth   # 2x super-resolution enhancement model
`-- vgg                         # VGG feature extraction model
    `-- vgg.pth                 # VGG network pre-trained weights

🎮 Run Inference

for blind face restoration

python scripts/inference.py \
		-i /path/to/video \
		-o /path/to/output_folder \
		--max_length 10 \
		--save_video_fps 24 \
		--ckpt_path /bfr/bfr_weight.pth \
		--bg_upsampler realesrgan \
		--save_video 

# or your videos has been aligned
python scripts/inference.py \
		-i /path/to/video \
		-o /path/to/output_folder \
		--max_length 10 \
		--save_video_fps 24 \
		--ckpt_path /bfr/bfr_weight.pth \
		--save_video \
		--has_aligned

for colorization & inpainting task

The current colorization & inpainting tasks only supports input of aligned faces. If a non-aligned face is input, it may lead to unsatisfactory final results.

# for colorization task
python scripts/inference_color_and_inpainting.py \
		-i /path/to/video_warped \
		-o /path/to/output_folder \
		--max_length 10 \
		--save_video_fps 24 \
		--ckpt_path /colorization/colorization_weight.pth \
		--bg_upsampler realesrgan \
		--save_video \
		--has_aligned

# for inpainting task
python scripts/inference_color_and_inpainting.py \
		-i /path/to/video_warped \
		-o /path/to/output_folder \
		--max_length 10 \
		--save_video_fps 24 \
		--ckpt_path /inpainting/inpainting_weight.pth \
		--bg_upsampler realesrgan \
		--save_video \
		--has_aligned

Test Data

Our test data can be accessed via the following links:

Baidu Netdisk: https://pan.baidu.com/s/1zMp3fnf6LvlRT9CAoL1OUw (Password: drhh)
Hugging Face Dataset: [https://huggingface.co

Related Skills

docs-writer

98.7k

`docs-writer` skill instructions As an expert technical writer and editor for the Gemini CLI project, you produce accurate, clear, and consistent documentation. When asked to write, edit, or revie

model-usage

330.3k

Use CodexBar CLI local cost usage to summarize per-model usage for Codex or Claude, including the current (most recent) model or a full model breakdown. Trigger when asked for model-level usage/cost data from codexbar, or when you need a scriptable per-model summary from codexbar cost JSON.

arscontexta

2.8k

Claude Code plugin that generates individualized knowledge systems from conversation. You describe how you think and work, have a conversation and get a complete second brain as markdown files you own.

Assume the personality of the Persona described in any of the document available in the @~/.ai/personas directory.

fudan-generative-vision

View profile

View on GitHub

GitHub Stars449

CategoryContent

Updated16d ago

Forks76

fudan-generative-vision/DicFace

Languages

Python

Security Score

85/100

Audited on Mar 7, 2026

No findings