Image generation techniques, such as generative adversarial networks (GANs), have become sufficiently sophisticated to cause growing concerns around the authenticity of images in the public domain. Although these generation techniques have been applied to a wide range of images, including images with objects and faces, there are comparatively few studies focused on their application to the generation and subsequent evaluation of Earth Observation (EO) data, such as aerial and satellite imagery. We examine the current state of aerial image generation by training state-of-the-art unconditional GAN models to generate realistic aerial imagery. We train PGGAN, StyleGAN2 and CoCoGAN models using the Inria Aerial Image benchmark dataset, and quantitatively assess the images they produce according to the Fréchet Inception Distance (FID) and the Kernel Inception Distance (KID). In a paired image human detection study we find that current synthesised EO images are capable of fooling humans and current performance metrics are limited in their ability to quantify the perceived visual quality of these images.

图像生成技术，例如生成对抗网络 (GAN)，已经变得足够复杂，足以引起人们对公共领域图像真实性的日益关注。尽管这些生成技术已应用于广泛的图像，包括带有物体和人脸的图像，但很少有研究关注它们在地球观测 (EO) 数据的生成和后续评估中的应用，例如航空和卫星图像. 我们通过训练最先进的无条件 GAN 模型来生成逼真的航拍图像来检查航拍图像生成的当前状态。我们使用 Inria Aerial Image 基准数据集训练 PGGAN、StyleGAN2 和 CoCoGAN 模型，并根据 Fréchet Inception Distance (FID) 和 Kernel Inception Distance (KID) 对它们产生的图像进行定量评估。在配对图像人体检测研究中，我们发现当前合成的 EO 图像能够欺骗人类，并且当前的性能指标在量化这些图像的感知视觉质量的能力方面受到限制。