DatasetsAirborne Laser Scans

Airborne Laser Scans

The Bavarian State Mapping Agency carries out area-wide airborne laser scanning campaigns at regular intervals and provides the point clouds for download via the open data portal:

Data provided by:
×
    Imagery
    Cesium ion
    Bing Maps Aerial
    Bing Maps Aerial with Labels
    Bing Maps Roads
    Sentinel-2
    Blue Marble
    Earth at night
    Natural Earth II
    Other
    ArcGIS World Imagery
    ArcGIS World Hillshade
    Esri World Ocean
    Open­Street­Map
    Stadia x Stamen Watercolor
    Stadia x Stamen Toner
    Stadia Alidade Smooth
    Stadia Alidade Smooth Dark
    Terrain
    Cesium ion
    WGS84 Ellipsoid
    Cesium World Terrain
    Pan view
    Left click + drag
    Zoom view
    Right click + drag, or
    Mouse wheel scroll
    Rotate view
    Middle click + drag, or
    CTRL + Left/Right click + drag
    Pan view
    One finger drag
    Zoom view
    Two finger pinch
    Tilt view
    Two finger drag, same direction
    Rotate view
    Two finger drag, opposite direction
    Apr 24 202503:19:15 UTC1xToday (real-time)Play ReversePlay ForwardPause
    Apr 24 2025 00:00:00 UTCApr 24 2025 06:00:00 UTCApr 24 2025 12:00:00 UTCApr 24 2025 18:00:00 UTCApr 25 2025 00:00:00 UTCApr 25 2025 06:00:00 UTC
    Apr 25 2025 06:00:00 UTC

    Point clouds streamed by envis.space

    The tiles can be downloaded with the following command:

    curl --compressed --remote-name-all "https://geodaten.bayern.de/odd_data/laser/{690_5335,690_5336,691_5335,691_5336}.laz"

    Simulated Airborne Laser Scans

    This dataset simulates airborne LiDAR scanning using the Helios++ toolkit and the high-quality LoD2 building models. To improve the neural network’s robustness in real-world conditions, noise and inter-building occlusions are deliberately included. The virtual sensor closely simulates the Leica HYPERION2+ system, with a survey flown at 400 m altitude by a virtual Cirrus SR22 aircraft. The training set encompasses 281,571 buildings and over 6.5 billion points from Munich, with an additional 10,000 buildings reserved for evaluation. Each building contains an average of 22,406 points. This dataset has been used for algorithm development in the PolyGNN project.

    Download