TL;DR本文提出一种改进的基于 GAN 的文本图像生成方法,通过优化感知损失函数,可以生成更具感染力、质量更高的鸟和花卉的合成图像。
Abstract
Recent approaches in generative adversarial networks (GANs) can automatically
synthesize realistic images from descriptive text. Despite the overall fair
quality, the generated images often expose visible flaws that lack structural
definition for an object of interest. In this paper, w