VividFace 🤖

This repository is the official implementation of the facial expression shadowing system in paper

VividFace: Real-Time and Realistic Facial Expression Shadowing for Humanoid Robots

Customized iOS App source code is available at VideoStreamer.

Real-World Examples of Realistic Imitation

🚀 Getting Started

🔧 Clone the Code and Set Up the Environment

git clone [email protected]:pi3-141592653/VividFace.git
cd VividFace

# create env using conda
conda create -n vividface python=3.9
conda activate vividface
# for cuda 12.1
conda install pytorch==2.4.0 torchvision==0.19.0 torchaudio==2.4.0 pytorch-cuda=12.1 -c pytorch -c nvidia

📦 Install Python Dependencies

pip install -r requirements.txt

📥 Pre-trained Models

You can download pre-trained models here:

🔗Base Models fine-tuned on X2C for 30 epochs.

🔗Mapping Network trained on X2C for 100 epochs, using ResNet18 as the feature extractor.

🚀 Run

python main.py

🤝 Contributing

We are actively updating and improving this repository. If you find any bugs or have suggestions, welcome to raise issues or submit pull requests (PR) 💖. If you find VividFace or X2CNet++ useful for your research, welcome to 🌟 this rep.