Abstract
Although Generative Adversarial Networks (GANs) have shown remarkable success in various tasks, they still face challenges in generating high quality images. In this paper, we propose Stacked Generative Adversarial Networks (StackGAN) aiming at generating high-resolution photo-realistic images. First, we propose a two-stage generative adversarial network architecture, StackGAN-v1, for text-to-image synthesis. The Stage-I GAN sketches the primitive shape and colors of the object based on given text description, yielding low-resolution images. The Stage-II GAN takes Stage-I results and text descriptions as inputs, and generates high-resolution images with photo-realistic details. Second, an advanced multi-stage generative adversarial network architecture, StackGAN-v2, is proposed for both conditional and unconditional generative tasks. Our StackGAN-v2 consists of multiple generators and discriminators in a tree-like structure; images at multiple scales corresponding to the same scene are generated from different branches of the tree. StackGAN-v2 shows more stable training behavior than StackGAN-v1 by jointly approximating multiple distributions. Extensive experiments demonstrate that the proposed stacked generative adversarial networks significantly outperform other state-of-the-art methods in generating photo-realistic images.
Abstract (translated)
尽管生成敌对网络（GAN）在各种任务中取得了显着的成功，但它们在生成高质量图像方面仍面临挑战。在本文中，我们提出了堆叠生成敌对网络（StackGAN），旨在生成高分辨率的照片般逼真的图像。首先，我们提出了一个两阶段生成对抗网络体系结构StackGAN-v1，用于文本到图像的合成。 Stage-I GAN根据给定的文字描述描绘对象的原始形状和颜色，产生低分辨率的图像。 Stage-II GAN将第一阶段的结果和文字描述作为输入，并生成具有照片逼真细节的高分辨率图像。其次，提出了一种先进的多阶段生成对抗网络体系结构StackGAN-v2，用于有条件和无条件的生成任务。我们的StackGAN-v2由多个生成器和鉴别器组成，具有树状结构;从树的不同分支生成对应于相同场景的多个尺度的图像。通过共同逼近多个分布，StackGAN-v2比StackGAN-v1显示更稳定的训练行为。大量实验表明，所提出的堆叠生成对抗网络在生成照片逼真图像方面明显优于其他最先进的方法。
URL
https://arxiv.org/abs/1710.10916
