CVLGIVJul 31, 2020

Neural Style Transfer for Remote Sensing

arXiv:2007.15920v1
AI Analysis

This is an incremental application of existing neural style transfer methods to remote sensing data for artistic map creation.

The study tackled the problem of creating artistic maps from satellite images by applying neural style transfer to segmented classes like land and water, resulting in a collage of stylized images.

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.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes