Using Photorealistic Face Synthesis and Domain Adaptation to Improve Facial Expression Analysis

This repository includes the training and testing codes for: "Using Photorealistic Face Synthesis and Domain Adaptation to Improve Facial Expression Analysis".

Dependencies

• Python2.7
• PyTorch
• torchvision
• OpenCV
• Dlib

Datasets

• The Binghamton University 3D Facial Expression Database (BU-3DFE)
• The Radboud Faces Database (RaFD)
• The MUG dataset
• Oulu-CASIA VIS

Usage:

Clone the repository

$ git clone https://github.com/BehzadBozorgtabar/FSDA.git
cd master

Train

python synthesis.py --mode='train'

Test

python synthesis.py --mode='test'

Face Synthesis Model