Real or Not Real, that is the Question
This provides an incremental improvement to GANs for researchers and practitioners in generative modeling.
The paper tackles the problem of improving generative adversarial networks by treating realness as a random variable estimated from multiple angles, resulting in a method called RealnessGAN that achieves improvements on synthetic and real-world datasets and enables DCGAN to generate realistic 1024*1024 resolution images from scratch.
While generative adversarial networks (GAN) have been widely adopted in various topics, in this paper we generalize the standard GAN to a new perspective by treating realness as a random variable that can be estimated from multiple angles. In this generalized framework, referred to as RealnessGAN, the discriminator outputs a distribution as the measure of realness. While RealnessGAN shares similar theoretical guarantees with the standard GAN, it provides more insights on adversarial learning. Compared to multiple baselines, RealnessGAN provides stronger guidance for the generator, achieving improvements on both synthetic and real-world datasets. Moreover, it enables the basic DCGAN architecture to generate realistic images at 1024*1024 resolution when trained from scratch.