Implementation

We were fascinated by the possibility of generating new and non-existent but realistic images using conditional adversarial neural networks that remembers a certain set of features from what it has seen in the past; the same process that we humans undergo when we dream. Taking inspiration from the given examples, we applied a pre-defined color scheme to geographic data (OpenStreetMap) using Mapbox Studio: roads, green spaces, buildings, water were styled with different colours (black, green, red, blue), so that the neural network (NN) could compare these to aerial images and learn the correspondence between them. We then used vvvv as a tool to collect both satellite imagery and the associated labeled map tiles. We trained a conditional generative adversarial network, using pix2pix to reconstruct the satellite imagery from its map tiles. The sample below on the right shows the reconstructed sattelite image of the given map tile, closely resembling to the original on the left.