Neural Style Transfer for Remote Sensing

TL;DR

This paper adapts neural style transfer to satellite images by segmenting content, applying style transfer per class, and creating artistic collages, enabling artistic map creation from remote sensing data.

Contribution

It introduces a novel method combining semantic segmentation with neural style transfer for artistic satellite image synthesis.

Findings

Effective artistic map generation from satellite images

Preservation of semantic content during stylization

Potential applications in remote sensing and visualization

Abstract

The well-known technique outlined in the paper of Leon A. Gatys et al., A Neural Algorithm of Artistic Style, has become a trending topic both in academic literature and industrial applications. Neural Style Transfer (NST) constitutes an essential tool for a wide range of applications, such as artistic stylization of 2D images, user-assisted creation tools and production tools for entertainment applications. The purpose of this study is to present a method for creating artistic maps from satellite images, based on the NST algorithm. This method includes three basic steps (i) application of semantic image segmentation on the original satellite image, dividing its content into classes (i.e. land, water), (ii) application of neural style transfer for each class and (iii) creation of a collage, i.e. an artistic image consisting of a combination of the two stylized image generated on the previous step.