Large-scale terrain generation remains a labor-intensive task in computer graphics. We introduce Geodiffussr, a flow-matching pipeline that synthesizes text-guided texture maps while strictly adhering to a supplied Digital Elevation Map (DEM). The core mechanism is multi-scale content aggregation (MCA): DEM features from a pretrained encoder are injected into UNet blocks at multiple resolutions to enforce global-to-local elevation consistency. Compared with a non-MCA baseline, MCA markedly improves visual fidelity and strengthens height-appearance coupling (FID ↓ 49.16%, LPIPS ↓ 32.33%, ΔdCor ↓ to 0.0016). To train and evaluate Geodiffussr, we assemble a globally distributed, biome- and climate-stratified corpus of triplets pairing SRTM-derived DEMs with Sentinel-2 imagery and vision-grounded natural-language captions that describe visible land cover. We position Geodiffussr as a strong baseline and step toward controllable 2.5D landscape generation for coarse-scale ideation and previz, complementary to physically based terrain and ecosystem simulators.
@article{arxiv.2511.23029,
title = {Geodiffussr: Generative Terrain Texturing with Elevation Fidelity},
author = {Tai Inui and Alexander Matsumura and Edgar Simo-Serra},
journal= {arXiv preprint arXiv:2511.23029},
year = {2025}
}