Seamless Satellite-image Synthesis

Zhu, Jialin; Kelly, Tom

Seamless Satellite-image Synthesis

Files

v40i7pp193-204.pdf (21.24 MB)

additional_materials.zip (313.81 MB)

Date

2021

Authors

Zhu, Jialin
Kelly, Tom

Publisher

The Eurographics Association and John Wiley & Sons Ltd.

Abstract

We introduce Seamless Satellite-image Synthesis (SSS), a novel neural architecture to create scale-and-space continuous satellite textures from cartographic data. While 2D map data is cheap and easily synthesized, accurate satellite imagery is expensive and often unavailable or out of date. Our approach generates seamless textures over arbitrarily large spatial extents which are consistent through scale-space. To overcome tile size limitations in image-to-image translation approaches, SSS learns to remove seams between tiled images in a semantically meaningful manner. Scale-space continuity is achieved by a hierarchy of networks conditioned on style and cartographic data. Our qualitative and quantitative evaluations show that our system improves over the state-of-the-art in several key areas. We show applications to texturing procedurally generation maps and interactive satellite image manipulation.

        @article{10.1111:cgf.14413
,
journal = {Computer Graphics Forum},
title = {{Seamless Satellite-image Synthesis
}},
author = {Zhu, Jialin and 
Kelly, Tom
},
year = {2021
},
publisher = {The Eurographics Association and John Wiley & Sons Ltd.
},
ISSN = {1467-8659
},
DOI = {10.1111/cgf.14413
}
}