Image To Image Translation: Generating Maps From Satellite Images

Abstract

Generation of maps from satellite images is conventionally done by a range of tools. Maps became an important part of life whose conversion from satellite images may be a bit expensive but Generative models can pander to this challenge. These models aim at finding the patterns between the input and output image. Image to image translation is employed to convert satellite images to the corresponding maps. Different techniques for the image to image translations like Generative adversarial networks, Conditional adversarial networks, and Co-Variational Autoencoders are used to generate the corresponding human-readable maps for that region, which takes a satellite image at a given zoom level as its input. We are training our model on Conditional Generative Adversarial Network which comprises of Generator model which generates fake images while the discriminator tries to classify the image as real or fake and both these models are trained synchronously in an adversarial manner where both try to fool each other and result in enhancing model performance.

Keywords: Generative Model, Conditional Generative Adversarial Network, Co-Variational Auto Encoders

JEL Classification: C0