SensatUrban: Urban-Scale Photogrammetric Point Clouds for 3D Modeling

SensatUrban provides urban-scale photogrammetric point clouds for 3D scene understanding, released by Qingyong Hu in conjunction with CVPR 2021 and IJCV 2022 publications. The data covers large city areas to support benchmarks in semantic segmentation and urban modeling.

Use Cases

• Semantic segmentation of urban structures using X, Y, Z coordinates and color features
• 3D city modeling from large-scale photogrammetric point clouds
• Benchmarking deep learning architectures for city-scale point cloud processing

Strengths

• Peer-reviewed research foundation (CVPR 2021, IJCV 2022)
• Urban-scale spatial coverage for city modeling
• Permissive MIT license for research and commercial use

Limitations

• Photogrammetric point clouds typically exhibit higher noise levels compared to LiDAR-derived data
• Specific point counts and geographic coordinates are not detailed in the primary metadata

Provenance

Source

Qingyong Hu (CVPR 2021 / IJCV 2022)

Collection Method

Photogrammetry

Freshness

Last updated July 2022; based on 2021-2022 research publications.

Geography

Urban environments