Stylized Projected GAN: A Novel Architecture for Fast and Realistic Image Generation

TL;DR

This paper introduces Stylized Projected GANs, an improved architecture combining Style GANs and Fast GAN features to enhance image quality and training efficiency in generative adversarial networks.

Contribution

It presents a novel architecture that integrates Style GAN mapping networks with Skip Layer Excitation to reduce artifacts and improve image quality in projected GANs.

Findings

Reduced artifacts in generated images

Faster training convergence

Improved image realism

Abstract

Generative Adversarial Networks are used for generating the data using a generator and a discriminator, GANs usually produce high-quality images, but training GANs in an adversarial setting is a difficult task. GANs require high computation power and hyper-parameter regularization for converging. Projected GANs tackle the training difficulty of GANs by using transfer learning to project the generated and real samples into a pre-trained feature space. Projected GANs improve the training time and convergence but produce artifacts in the generated images which reduce the quality of the generated samples, we propose an optimized architecture called Stylized Projected GANs which integrates the mapping network of the Style GANs with Skip Layer Excitation of Fast GAN. The integrated modules are incorporated within the generator architecture of the Fast GAN to mitigate the problem of artifacts in the generated images.