BEGAN: Boundary Equilibrium Generative Adversarial Networks
This addresses the problem of unstable training and poor image quality in GANs for researchers and practitioners in computer vision.
The paper tackles training instability and visual quality in generative adversarial networks by proposing an equilibrium enforcing method with a Wasserstein-based loss, achieving high visual quality and new milestones in image generation at higher resolutions.
We propose a new equilibrium enforcing method paired with a loss derived from the Wasserstein distance for training auto-encoder based Generative Adversarial Networks. This method balances the generator and discriminator during training. Additionally, it provides a new approximate convergence measure, fast and stable training and high visual quality. We also derive a way of controlling the trade-off between image diversity and visual quality. We focus on the image generation task, setting a new milestone in visual quality, even at higher resolutions. This is achieved while using a relatively simple model architecture and a standard training procedure.