{"slug": "enhancing-photogrammetric-digital-surface-models-with-pretrained-diffusion-and", "title": "Enhancing Photogrammetric Digital Surface Models with Pretrained Diffusion Models and Multimodal Conditioning", "summary": "Researchers propose enhancing photogrammetric Digital Surface Models (DSMs) derived from satellite stereo imagery by using pretrained diffusion models with multimodal conditioning, addressing noise, outliers, and voids that contaminate large-scale 3D maps. The approach contrasts with aerial LiDAR, which provides high-accuracy elevation measurements at a substantially higher cost.", "body_md": "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 substant", "url": "https://wpnews.pro/news/enhancing-photogrammetric-digital-surface-models-with-pretrained-diffusion-and", "canonical_source": "https://aiflash.com/news/127673/", "published_at": "2026-09-28 09:00:04+00:00", "updated_at": "2026-09-28 09:18:29.387894+00:00", "lang": "en", "topics": ["computer-vision", "machine-learning", "artificial-intelligence", "generative-ai"], "entities": [], "also_reported_by": [], "alternates": {"html": "https://wpnews.pro/news/enhancing-photogrammetric-digital-surface-models-with-pretrained-diffusion-and", "markdown": "https://wpnews.pro/news/enhancing-photogrammetric-digital-surface-models-with-pretrained-diffusion-and.md", "text": "https://wpnews.pro/news/enhancing-photogrammetric-digital-surface-models-with-pretrained-diffusion-and.txt", "jsonld": "https://wpnews.pro/news/enhancing-photogrammetric-digital-surface-models-with-pretrained-diffusion-and.jsonld"}}