Towards Real-Time Lightweight Facial Reconstruction Model

By Victor Hernández-Manrique, Miguel González-Mendoza, EugeniaVirtualHumans.

[Updates]

• 2024.02.21: Finished documentation of 3DDFA-V1 XLR8TD for its installation and usage.
• 2024.01.31: Creation of repository "3DDFA-V1 XLR8TD"

Requirements

• Ubuntu >=23.10
• Anaconda >=24.1.0

Usage

1. Clone this repo

   git clone https://github.com/VictorHManrique/3DDFA-V1-XLR8TD.git
   

   cd 3DDFA-V1-XLR8TD
   

   Then, download dlib landmark pre-trained model in Google Drive or Baidu Yun, and put it into models directory. (To reduce this repo's size)

2. Create Conda Environment

   conda env create -f environment.yml
   

3. Activate Conda Environment

   conda activate XLR8TD
   

4. Build cython module (just one line for building)

   cd utils/cython
   

   python3 setup.py build_ext -i
   

5. Return to Main

   cd ../..
   

6. Run the UI

   python3 xlr8td.py
   

7. Once the UI is displayed, click on the XLR8TD button.