Seamless Satellite-image Synthesis

TL;DR

Seamless Satellite-image Synthesis (SSS) introduces a neural architecture that generates continuous, large-scale satellite textures from cartographic data, overcoming tile limitations and ensuring scale-space consistency for applications like map texturing and image manipulation.

Contribution

The paper presents a novel neural network system that produces seamless, scale-consistent satellite textures from cartographic data, addressing tile limitations and improving over existing methods.

Findings

Outperforms state-of-the-art in satellite texture synthesis

Produces seamless textures over large spatial extents

Enables applications in map texturing and image manipulation

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 While 2D map data is cheap and easily synthesized, accurate satellite imagery is expensive and often unavailable or out of date.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.