Research
Enhancing Photogrammetric Digital Surface Models with Pretrained Diffusion Models and Multimodal Conditioning
arXiv:2609.31199v1 Announce Type: cross Abstract: Large-scale Digital Surface Models (DSMs) can be produced cost-effectively from satellite images via stereo-photogrammetry. However, the resulting 3D
arXiv:2609.31199v1 Announce Type: cross Abstract: Large-scale Digital Surface Models (DSMs) can be produced cost-effectively from satellite images via stereo-photogrammetry. However, the resulting 3D maps are often contaminated by noise, outliers, and voids. On the other hand, aerial LiDAR provides high-accuracy elevation measurements at a substantially higher cost. In this work, we study diffusion models conditioned both on photogrammetric DSMs and Pleiades imagery to refine vertically co-registered DSMs. We introduce a modified Stable Diffusion 3 architecture with a pruned text stream and a patch-wise normalization strategy, enabling stable training on LiDAR data and transfer from natural images to elevation maps. Experiments in French cities demonstrate that multimodal conditioning improves elevation accuracy, reducing Dense Urban RMSE from 6.00 to 3.45 m in the in-context cities and from 4.16 to 2.77 m in the held-out city of Bordeaux.
Related
- SharpSplat: Edge-Regularized 3D Gaussian Splatting for High Fidelity Urban Building Reconstruction from UAV images
- Compression as Adaptation: Implicit Visual Representation with Diffusion Foundation Models
- Guided Super-Resolution of Digital Elevation Models with Diffusion-Based Image Generators
- Diffusion Models for Hyperspectral Image Analysis: A Comprehensive Review
Source: arXiv cs.CV | 2026-09-28