Skip to main content

Guide to Overture Buildings

Overview

The Overture Maps buildings theme describes human-made structures with roofs or interior spaces that are permanently or semi-permanently in one place (source: OSM building definition). Overture's goal is to provide the world's most comprehensive set of building structures compiled from the best available open data sources, covering all the world's buildings. The theme includes two feature types:

  • building: The most basic form of a building feature. The geometry is expected to be the most outer footprint—roofprint if traced from satellite/aerial imagery—of a building. Buildings have a boolean attribute has_parts that describe whether there are any associated building parts.
  • building_part: A single part of a building. Building parts may share the same properties as buildings. A building part is associated with a parent building via a building_id.

Data access and retrieval

Overture's building and building_part datasets are freely available on both Amazon S3 and Microsoft Azure Blob Storage at the locations listed below. We provide a comprehensive guide to accessing Overture data in our documentation.

ProviderLocation
Amazon S3
s3://overturemaps-us-west-2/release/2025-09-24.0/theme=buildings/type=building/*
Azure Blob Storage
https://overturemapswestus2.blob.core.windows.net/release/2025-09-24.0/theme=buildings/type=building/*

Use cases

Our buildings data is intended to support multiple use cases, as defined and prioritized by various Overture members, but may be used for other use cases as imagined by Overture data users assuming they comply with the open data license.

  • 2D Visualization: Display of the buildings in a 2D map display, perhaps symbolized by other properties.
  • 3D Visualization: Display of the buildings (and parts) in a 3D (or 2.5D) display, extruded by building height or levels.
  • Data Enrichment: Enable end users to enrich the buildings with additional attributes using GERS ID.
  • Spatial Analysis: Enable end users to perform analysis to create derivative datasets or train AI models.

Dataset schema

Overture releases its data as GeoParquet files. The building and building_part datasets have slightly different schemas, and the column definitions for those data files are described below. For more detailed information about the buildings schema see Overture schema reference documentation.

Column definitions for the building and building_part datasets
columntypedescription
idstringA feature ID that may be associated with the Global Entity Reference System (GERS) if—and-only-if the feature represents an entity that is part of GERS.
geometrybinaryA building's geometry is defined as its footprint or roofprint (if traced from aerial/satellite imagery). It MUST be a Polygon or MultiPolygon as defined by the GeoJSON schema.
bboxstructArea defined by two longitudes and two latitudes: latitude is a decimal number between -90.0 and 90.0; longitude is a decimal number between -180.0 and 180.0.
versionintegerVersion number of the feature, incremented in each Overture release where the geometry or attributes of this feature changed.
sourcesstructThe array of source information for the properties of a given feature. Each source object lists the property in JSON Pointer notation and the dataset from which that specific value originated.
subtypestringA broad category of the building type and purpose.
namesstructThe name associated with the feature. The first entry in the array of names must have a "local" language.
classstringFurther delineation of the building's built purpose.
levelintegerThe building feature's Z-order, i.e., stacking order. A Z-order of 0 is ground level.
has_partsbooleanFlag indicating whether the building has parts.
is_undergroundbooleanWhether the entire building or part is completely below ground. This is useful for rendering which typically omits these buildings or styles them differently because they are not visible above ground. This is different than the level column which is used to indicate z-ordering of elements and negative values may be above ground.
heightdoubleHeight of the building or part in meters. The height is the distance from the lowest point to the highest point.
num_floorsintegerNumber of above-ground floors of the building or part.
num_floors_undergroundintegerNumber of below-ground floors of the building or part.
min_heightdoubleThe height of the bottom part of building in meters. Used if a building or part of building starts above the ground level.
min_floorintegerThe "start" floor of a building or building part. Indicates that the building or part is "floating" and its bottom-most floor is above ground level, usually because it is part of a larger building in which some parts do reach ground level.
facade_colorstringThe color (name or color triplet) of the facade of a building or building part in hexadecimal.
facade_materialstringThe outer surface material of building facade.
roof_materialstringThe outermost material of the roof.
roof_shapestringThe shape of the roof.
roof_directiondoubleBearing of the roof ridge line.
roof_orientationstringOrientation of the roof shape relative to the footprint shape. Either "along" or "across."
roof_colorstringThe color (name or color triplet) of the roof of a building or building part in hexadecimal.
roof_heightdoubleThe height of the building roof in meters. This represents the distance from the base of the roof to the highest point of the roof.
filenamestringName of the file being queried.
themevarcharName of the Overture theme being queried.
typevarcharName of the Overture feature type being queried.

How we build the dataset

Sources

Currently, the Overture building dataset is a combination of the following open building datasets. (The building_part dataset comes from one source: OpenStreetMap.)

SourceTypeConflation PriorityCount
OpenStreetMapCommunity-contributed1~656 Million
Esri Community MapsCommunity-contributed2~17.5 Million
Instituto Geográfico Nacional (España)National dataset3~12.9 Million
City of Vancouver, CanadaMunicipal dataset4~17 Thousand
Google Open BuildingsML-derived roofprints (>90% precision)5~350 Million
MicrosoftML-derived roofprints6~805 Million
Google Open BuildingsML-derived roofprints (<90% precision)7~650 Million
Buildings in East Asian CountriesML-derived roofprints8~213 Million

Quality and prioritization

To help ensure quality as well as quantity, the conflation process for the building dataset prioritizes community contributed data over machine learning (ML) generated data. The highest priority dataset used in conflation is OpenStreetMap. This ensures that any data added to OpenStreetMap based on local knowledge or manual editing of ML data is prioritized with each update of Overture Maps buildings. If there is a quality issue in one of the Overture Maps buildings, it can be addressed by adding, updating, or deleting that same building structure in OpenStreetMap and it will be reflected in the next Overture Maps release.

Many Overture Maps buildings are derived from ML sources (e.g. Microsoft and Google Open Buildings). These ML datasets are known to include some detections that do not qualify as building structures as defined above. These might be shipping containers, car ports, solar panels, or other objects that resemble buildings in satellite or aerial imagery. To remove most of these invalid features from the buildings theme, the Overture Maps conflation process excludes ML features below a certain size that are unlikely to be valid buildings. These exclusion rules might result in some valid features being missed but, on balance, improve the quality of the buildings theme. Missing features can be added through OpenStreetMap editing (e.g. Rapid editor accessing ML features).

Conflation and matching

As part of the conflation process, features in the open data sources are matched and assigned a GERS ID. The intent is to have a single, stable GERS ID for each building feature. If there are multiple sources for an individual building feature (e.g. the Lincoln Memorial), then that building feature in each data source should be assigned the same GERS ID, whether that feature is included in the Overture buildings theme that is released or not.

The matching step in the conflation process is based on the geometry of the building features, using a metric called Intersection over Union (IoU). Buildings are considered a match if the IoU score exceeds 50%. The score is calculated by dividing the area where the two building shapes overlap by the total area they cover combined. On this scale, a 100% score signifies a perfect overlap, whereas disconnected (non-overlapping) geometries score 0%.

The visualization below shows Overture buildings data looking across the US-Mexico border toward San Diego. Notice how Esri and OSM buildings appear in big blocks while the Google and Microsoft buildings appear to mix together. This is a product of our conflation process that prioritizes community contributed data first and then "fills in" the rest of the map with the best ML data available.

OpenStreetMap | Esri Community Maps | Microsoft ML Buildings | Google Open Buildings

© OpenStreetMap contributors, OvertureMaps Foundation

Licensing

The Overture Maps buildings theme is provided under the ODbL license, largely because the primary OpenStreetMap data is provided under that license. This requires that other data sources that are included in the buildings theme are also provided under ODbL or a license that is compatible with ODbL, such as CC BY 4.0. Overture Maps determine if potential sources of open data that would expand coverage or improve quality are provided under a license that is compatible with ODbL before adding to the conflation process. For more information, see the licensing and attribution section of our documentation.