/StarGAN_TensorFlow_2.0

Expression Translation using StarGAN proposed in the paper StarGAN: Unified Generative Adversarial Networks for Multi-Domain Image-to-Image Translation

Primary LanguagePython

StarGAN for Image-to-Image Expression Translation

Introduction

StarGAN, is a novel and scalable approach that can perform image-to-image translations for multiple domains using only a single model.Such a unified model architecture of StarGAN allows simultaneous training of multiple datasets with different domains within a single network. This leads to StarGAN’s superior quality of translated images. In this paper I use the StarGan architecture for expression synthesis by generating new images with different expressions from a single image.

Requirements

  • Python 3.6
  • Tensorflow 2.0
  • CelebA dataset
  • RAFD dataset