{"ID":2835434,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2511.23029","arxiv_id":"2511.23029","title":"Geodiffussr: Generative Terrain Texturing with Elevation Fidelity","abstract":"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 $\\downarrow$ 49.16%, LPIPS $\\downarrow$ 32.33%, $Δ$dCor $\\downarrow$ 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.","short_abstract":"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 fr...","url_abs":"https://arxiv.org/abs/2511.23029","url_pdf":"https://arxiv.org/pdf/2511.23029v1","authors":"[\"Tai Inui\",\"Alexander Matsumura\",\"Edgar Simo-Serra\"]","published":"2025-11-28T09:52:44Z","proceeding":"cs.GR","tasks":"[\"cs.GR\",\"cs.CV\"]","methods":"[]","has_code":false}