DeKH: German Hospital 3D Point Clouds with BIM Models

DeKH (German Hospital Dataset) is a multi-scene dataset of real hospital environments comprising high-resolution 3D point clouds with semantic annotations and ground-truth IFC BIM models. It was introduced by RPTU-FGMB alongside the BIMStruct3D pipeline and was accepted at EC3 2026. The dataset covers four distinct hospital scenes across three buildings.

Use Cases

• Training semantic segmentation models for 3D point clouds based on the provided semantic annotations.
• Developing and benchmarking automated building information modeling (BIM) reconstruction pipelines based on the ground-truth IFC models.
• Researching 3D scene understanding and object detection in complex, real-world indoor environments like hospitals.

Strengths

• Includes ground-truth IFC BIM models for validation of reconstruction tasks.
• Covers four distinct hospital scenes across three buildings, suggesting scene variety.
• Contains high-resolution 3D point clouds with semantic annotations.

Limitations

• Column-level documentation is absent; field semantics must be inferred after download.
• Row count and total dataset size are unknown, which may limit suitability assessment.

Provenance

Source

RPTU-FGMB

Collection Method

Likely collected via 3D scanning of real hospital environments.

Freshness

Last updated 2026-05-19 09:10:33; freshness should be verified.

Geography

Germany (inferred from dataset title and description).