An Image Style Diversified Synthesis Method Based on Generative Adversarial Networks
Zujian Yang, Zhao Qiu · Electronics · 2022
Existing research shows that there are many mature methods for image conversion in different fields. However, when the existing methods deal with images in multiple image domains, the robustness and scalability of images are often limited. We propose a novel and scalable approach, using a generative adversarial networks (GANs) model that can transform images across multiple domains, to address the above limitations. Our model can be trained on image datasets with different domains in a single network, with the ability to translate images and the ability to flexibly translate input images to any desired target domain. Our model is mainly composed of a generator, discriminator, style encoder, and a mapping network. The datasets use the celebrity face dataset CelebA-HQ and the animal face dataset AFHQ, and the evaluation criteria use FID and LPIPS to evaluate the images generated by the model. Experiments show that our model can generate a rich variety of high-quality images, and there is still some room for improvement.