Stylized Projected GAN: A Novel Architecture for Fast and Realistic Image Generation
This work addresses image generation quality issues for researchers and practitioners, but it appears incremental as it builds on existing methods like Projected GANs, StyleGAN, and FastGAN.
The paper tackles the problem of artifacts in generated images from Projected GANs, which reduce quality, by proposing Stylized Projected GANs, an optimized architecture that integrates StyleGAN's mapping network and FastGAN's skip layer excitation to mitigate these artifacts.
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.