# Transferring Multiscale Map Styles Using Generative Adversarial Networks

## TL;DR

This paper introduces a GAN-based framework for transferring styles across different map scales, enabling the creation of stylized maps from various visual sources while evaluating the preservation of original design features.

## Contribution

The paper presents a novel multiscale map style transfer method using GANs and a deep CNN classifier for evaluation, addressing a new application area in digital cartography.

## Key findings

- GANs effectively transfer styles across multiple map scales
- Deep CNN classifier assesses style preservation with high accuracy
- Challenges remain in fully capturing complex stylistic nuances

## Abstract

The advancement of the Artificial Intelligence (AI) technologies makes it possible to learn stylistic design criteria from existing maps or other visual art and transfer these styles to make new digital maps. In this paper, we propose a novel framework using AI for map style transfer applicable across multiple map scales. Specifically, we identify and transfer the stylistic elements from a target group of visual examples, including Google Maps, OpenStreetMap, and artistic paintings, to unstylized GIS vector data through two generative adversarial network (GAN) models. We then train a binary classifier based on a deep convolutional neural network to evaluate whether the transfer styled map images preserve the original map design characteristics. Our experiment results show that GANs have a great potential for multiscale map style transferring, but many challenges remain requiring future research.