GeoRID: Role-Specialized Instruction Decomposition with Compact Visual Tokens for Complex-Instruction Remote Sensing Image Synthesis
Environmental monitoring, urban-growth rehearsal, and disaster-scenario simulation often need a satellite or aerial scene drawn from a compound geospatial instruction: object counts, relative bearings, land-cover mosaics, and a stated ground sample distance (GSD). Existing remote sensing text-to-image (T2I) models flat...