Urban-StyleGAN: Learning to Generate and Manipulate Images of Urban Scenes
Urban-StyleGAN: Learning to Generate and Manipulate Images of Urban Scenes
A promise of Generative Adversarial Networks (GANs) is to provide cheap photorealistic data for training and validating AI models in autonomous driving. Despite their huge success, their performance on complex images featuring multiple objects is understudied. While some frameworks produce high-quality street scenes with little to no control over the …