zhu-xlab/GlobalBuildingAtlas resource

Health v2 · maintenance only

Flags: no_license

Adoption not part of the score

2198 stars · 211 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

GlobalBuildingAtlas is an open dataset providing global building polygons, height attributes, and LoD1 3D building models derived via machine learning. The data is split across HuggingFace and mediaTUM due to mixed ODbL and CC BY-NC 4.0 licensing of its components.

Use cases

• download global building footprint polygons for urban analysis
• get LoD1 3D building models for city modeling
• estimate building heights worldwide for energy or flood studies
• visualize global 3D buildings in a web viewer
• combine building footprints with height maps in GIS
• analyze urban density and built environment at global scale

When to choose

• you need worldwide building polygons or 3D models rather than a single city or country
• you can accept machine-learning-derived data with some errors
• your use case is compatible with ODbL and CC BY-NC 4.0 licenses

When to avoid

• you need commercially licensed data (parts are CC BY-NC, non-commercial)
• you require survey-grade accuracy rather than ML-derived estimates
• you need a single consolidated download without handling split license parts

Facets

dataset · maturity active

geospatial machine-learning data-science data-science machine-learning cross-platform building-footprints 3d-buildings lod1 global-dataset urban-mapping height-maps geo open-data geospatial maps web-server

Member repositories

For agents

markdown · JSON · MCP: product_card(name="zhu-xlab/GlobalBuildingAtlas")