Seamless Satellite-image Synthesis
This addresses the high cost and unavailability of accurate satellite imagery for applications like procedurally generated maps and interactive manipulation.
The paper tackles the problem of generating seamless, scale-and-space continuous satellite textures from cartographic data, achieving improvements over state-of-the-art methods in key areas through qualitative and quantitative evaluations.
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 While 2D map data is cheap and easily synthesized, accurate satellite imagery is expensive and often unavailable or out of date.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.