Geodiffussr: Generative Terrain Texturing with Elevation Fidelity

TL;DR

Geodiffussr is a novel flow-matching pipeline that synthesizes terrain textures guided by text and strictly adheres to elevation data, significantly improving visual fidelity and elevation consistency in large-scale terrain generation.

Contribution

We introduce Geodiffussr, a new method combining multi-scale content aggregation with text-guided synthesis for terrain texturing aligned with elevation maps.

Findings

MCA improves visual fidelity over baseline

Height-appearance coupling is significantly enhanced

The method provides a controllable approach for terrain generation

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%, $\Delta$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.