:cityscape: LOD3 Road Space Models
Semantic models of the road spaces in the inner city of Ingolstadt in Germany at the level of detail 3:

:rocket: Getting Started
Download the semantic models by cloning the repo:
git clone --depth 1 [email protected]:savenow/lod3-road-space-models.git
:inbox_tray: Datasets
- models/road-network/opendrive
- Content: Road network with roadside objects
- Source: Demo dataset by the company 3D Mapping Solutions
- Conceptual data model: ASAM OpenDRIVE 1.4
- Encoding: XML
- License:
CC BY-NC-SA 4.0
- models/road-network/citygml
- Content: Road network with roadside objects
- Source: Converted from OpenDRIVE demo dataset to CityGML 2.0 and 3.0 using the tool r:trån
- Conceptual data model: OGC CityGML 2.0 and 3.0
- Encoding: GML
- License:
CC BY-NC-SA 4.0
- models/building/lod3
- Content: Over 50 LOD3 building models
- Source: Manually modeled based on the MLS point clouds by 3D Mapping Solutions
- Conceptual data model: OGC CityGML 2.0 and 3.0
- Encoding: GML
- License:
CC BY-SA 4.0
- models/building/lod2
- Content: 4 tiles of LOD2 building models
- Source: Open data portal of the Bavarian State Mapping Agency
- Conceptual data model: OGC CityGML 2.0 and 3.0
- Encoding: GML
- License:
CC BY 4.0
:mag: Modeling Details
The LOD3 building models were manually modeled using the tool SketchUp with the CityEditor extension.
For this, mobile laser scanning (MLS) point clouds by the company 3D Mapping Solutions GmbH with a relative accuracy of 1-3 cm served as the basis for modeling.
The SketchUp project files are also provided along with a creation guideline that documents the entire modeling process.
Further information:

:books: Citation
If you use the datasets in your research, please cite the following article:
@article{schwabRadiometricFingerprinting2026,
author = {Benedikt Schwab and Thomas H. Kolbe},
title = {Radiometric fingerprinting of object surfaces using mobile laser scanning and semantic 3D road space models},
journal = {International Journal of Applied Earth Observation and Geoinformation},
volume = {153},
pages = {105533},
year = {2026},
issn = {1569-8432},
doi = {https://doi.org/10.1016/j.jag.2026.105533},
url = {https://www.sciencedirect.com/science/article/pii/S1569843226004498},
keywords = {Radiometric fingerprint, Mobile laser scanning, Semantic road space model, CityGML, 3DSensorDB},
abstract = {Although semantic 3D city models are internationally available and becoming increasingly detailed, the incorporation of material information remains largely untapped. However, a structured representation of materials and their physical properties could substantially broaden the application spectrum and analytical capabilities for urban digital twins. At the same time, the growing number of repeated mobile laser scans of cities and their street spaces yields a wealth of observations influenced by the material characteristics of the corresponding surfaces. To leverage this information, we propose radiometric fingerprints of object surfaces by grouping LiDAR observations reflected from the same semantic object under varying distances, incidence angles, environmental conditions, sensors, and scanning campaigns. Our study demonstrates how 312.4million individual beams acquired across four campaigns using five LiDAR sensors on the Audi Autonomous Driving Dataset (A2D2) vehicle can be automatically associated with 6368 individual objects of the semantic 3D city model. The model comprises a comprehensive and semantic representation of four inner-city streets at Level of Detail (LOD) 3 with centimeter-level accuracy. It is based on the CityGML 3.0 standard and enables fine-grained sub-differentiation of objects. The extracted radiometric fingerprints for object surfaces reveal recurring intra-class patterns that indicate class-dominant materials. The semantic model, the method implementations, and the developed geodatabase solution 3DSensorDB are released under: https://github.com/tum-gis/sensordb}
}
:incoming_envelope: Feedback & Contributions
To expand and improve the dataset, feedback and contributions are always appreciated.
You can also contact me directly via mail [email protected].
:handshake: Thanks
Very special acknowledgments are due to Sophie Haas Goschenhofer and Olaf Wysocki, who worked diligently on the development of the methodology and the realization of the modeling.
评论