# Geodiffussr: Generative Terrain Texturing with Elevation Fidelity

arXiv: https://arxiv.org/abs/2511.23029 · HTML: https://mlsanity.com/paper/2511.23029/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 8 of its 18 references that are in the map.
- First posted on arXiv 28 Nov 2025.

## Builds on (most cited first, 8 of 8)

- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [Squeeze-and-Excitation Networks](https://mlsanity.com/paper/1709.01507/) (2017)
- [Real-ESRGAN: Training Real-World Blind Super-Resolution with Pure Synthetic Data](https://mlsanity.com/paper/2107.10833/) (2021)
- [FontDiffuser: One-Shot Font Generation via Denoising Diffusion with Multi-Scale Content Aggregation and Style Contrastive Learning](https://mlsanity.com/paper/2312.12142/) (2023)
- [Self-supervised pre-training enhances change detection in Sentinel-2 imagery](https://mlsanity.com/paper/2101.08122/) (2021)
- [MESA: Text-Driven Terrain Generation Using Latent Diffusion and Global Copernicus Data](https://mlsanity.com/paper/2504.07210/) (2025)
- [Terrain Diffusion Network: Climatic-Aware Terrain Generation with Geological Sketch Guidance](https://mlsanity.com/paper/2308.16725/) (2023)

## Abstract (arXiv)

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%, DeltadCor 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.