Generative Adversarial Networks (GANs) typically learn a distribution of
images in a large image dataset, and are then able to generate new images from
this distribution. However, each natural image has its own internal statistics,
captured by its unique distribution of patches. In this paper we propose an
"Internal GAN" (InGAN) - an image-specific GAN - which trains on a single input
image and learns its internal distribution of patches. It is then able to
synthesize a plethora of new natural images of significantly different sizes,
shapes and aspect-ratios - all with the same internal patch-distribution (same
"DNA") as the input image. In particular, despite large changes in global
size/shape of the image, all elements inside the image maintain their local
size/shape. InGAN is fully unsupervised, requiring no additional data other
than the input image itself. Once trained on the input image, it can remap the
input to any size or shape in a single feedforward pass, while preserving the
same internal patch distribution. InGAN provides a unified framework for a
variety of tasks, bridging the gap between textures and natural images.

本文提出了一种基于单张输入图片进行训练，学习其内部 patch distribution 的 Internal GAN 模型，通过 InGAN 生成大量不同大小、形状和长宽比的新自然图像，其内部 patch distribution 与输入图像保持一致，并能在保留本地大小形状的前提下，自动调整图像大小和形状。InGAN 模型基于无监督学习，只需要输入图像本身即可进行训练，提供了一种统一的纹理和自然图像的任务框架。