Synthesis of Satellite-Like Urban Images From Historical Maps Using Conditional GAN

One method for encouraging the public interest in the use of historical maps as a source of reliable knowledge is to represent them in a more familiar aspect, such as the style of the current-day popular application Google Maps' satellite view. We present a method for synthesizing satellite-images from historical maps, translating their visuals using conditional generative adversarial networks (conditional GANs). We discuss a typical representation of these dated documents to allow such translations. We observe how the semantics involved in the process influence the outcomes. Finally, we discuss the effective result of bringing the past to a familiar look for the viewer.