IoC3D: A Multi-Scenario 3D Point Cloud Dataset for Semantic Target Extraction and Construction Progress Monitoring via Scan-to-BIM Verification

IoC3D: A Multi-Scenario 3D point cloud dataset Semantic Target Extraction and Construction Progress Monitoring Dataset for Scan-to-BIM Verification IoC3D is a multi-scenario 3D point cloud dataset for semantic target extraction, Scan-to-BIM verification, and automated construction progress monitoring created within the Internet of Construction (IoC) project and further processed within the Cluster of Excellence CARE and the CARE Future Technologies Experimental Construction Site. The dataset documents several construction monitoring demonstrators and validation scenarios used for semantic target extraction, Scan-to-BIM registration, and automated object verification across multiple construction states. It contains: Planned 3D building models in OBJ format Synthetic point clouds generated from the planning models Real-world point cloud scans from multiple sensing technologies Target-extracted subsets Object verification labels Semantic segmentation labels Metadata for each scene Utility scripts and documentation The dataset is designed to support two sequential use cases: Target Extraction Construction Progress Monitoring via Object Verification The demonstrators and scientific background are documented in the publication IoC – Internet of Construction. The research and associated contributions related to IoC3D were carried out within the framework of the research project “Internet of Construction” (IoC), funded by the Federal Ministry of Education and Research of Germany within the funding initiative “Innovation for Production, Services and Work of Tomorrow” (funding number: 02P17D081). The project was supported by the project management agency Projektträger Karlsruhe (PTKA). The transformation of the acquired and simulated data into a structured benchmark dataset, including semantic labeling, object verification annotation generation, utility script development, preprocessing workflows, and dataset documentation, was carried out within the Cluster of Excellence CARE – Climate-Neutral and Resource-Efficient Construction. CARE is funded by the Deutsche Forschungsgemeinschaft (DFG, German Research Foundation) under Germany’s Excellence Strategy – EXC 3115 – 533767731. 1. Internet of Construction (IoC) The Internet of Construction (IoC) project investigated digital planning, fabrication, assembly, and construction monitoring workflows for industrialized construction processes. The project focused on: BIM-integrated construction workflows Automated construction monitoring Semantic scene understanding Scan-to-BIM verification Object-level construction progress assessment Digital twin generation and updating The resulting dataset combines several demonstrators and real-world validation scenarios for evaluating semantic target extraction and object verification pipelines. 1.1 Construction Monitoring Demonstrators The dataset contains three independent construction monitoring use cases. Use Case 01: Construction Progress Monitoring – Real Building Model Section The first use case serves as a validation scenario for automated construction progress monitoring. It consists of a scaled physical reconstruction of a real building section fabricated using modular 3D-printed construction elements. The setup was designed to evaluate: Semantic target extraction Registration robustness Object verification Detection of misplaced building components Seven construction states were recorded. One construction state intentionally contains a misplaced building component in order to evaluate the robustness of the object verification pipeline. The data acquisition was performed outdoors under realistic environmental conditions using a handheld Zeiss T-SCAN laser scanner. This validation scenario enables a comprehensive evaluation of: Target geometry extraction Registration quality Scan-to-BIM alignment Component-level verification under realistic multi-object construction conditions. Use Case 02: Construction Progress Monitoring – IoC Demonstrator The IoC demonstrator represents a large-scale research construction scenario for validating digital planning, fabrication, and assembly workflows. The demonstrator consists of: Concrete foundations Concrete columns Steel beam structures Timber beam frames Timber purlins The construction process was documented across multiple assembly stages. The pipeline is used to automatically verify mounted components and quantify geometric deviations between scan data and BIM-derived planning models. Applications include: Automated progress monitoring Scan-to-BIM verification Registration evaluation Component-level construction analysis Use Case 03: Construction Progress Monitoring – Steel Hall The third use case documents the construction progress of a real steel hall across multiple acquisition campaigns. The objective is the automated detection and digital progress assessment of mounted steel components. The dataset combines: BIM models Terrestrial laser scans Extracted target point clouds Object verification annotations The dataset enables direct comparison between: Planned BIM geometries Registered scan data Detected object geometries Applications include: Steel construction monitoring Change detection Temporal construction analysis Scan-to-BIM alignment 2. Benchmark Tasks Benchmark Task 1: Target Extraction The first task is to identify and extract the Object of Interest (OOI) from a full scene point cloud. The Object of Interest may represent: A building structure A demonstrator A machine An assembly of construction components A spatial storage region All target extraction scenes were acquired using an object-oriented scanning strategy. In this approach, the scanner is moved closely around the predefined region of interest to obtain high point density and geometric completeness. This acquisition strategy ensures that the scenes are captured under comparable conditions. Label Definition The target extraction task uses a three-class semantic labeling scheme: Label ID Class Name Description 0 Environment All points outside the region of interest and its supporting ground 1 Ground The ground surface directly underlying the region of interest 2 Target All points belonging to the Object of Interest The target class may consist of: A single object Multiple related objects A distributed component assembly A complete structure Only the relevant objects are labeled as target, while the supporting floor or terrain beneath them is always labeled as ground. Applications Semantic segmentation Target extraction Object detection Construction object localization Building extraction from complex scenes Benchmark Task 2: Progress Monitoring via Object Verification After extracting the target object, the extracted point cloud is registered with the corresponding planning model. Each planned component is compared against the scan data to determine whether sufficient evidence exists to confirm its presence. Label Definition The object verification task uses a binary labeling scheme: Label ID Class Name Description 0 Object not verified The component could not be confirmed in the scan data 1 Object verified The component was successfully identified in the scan data These labels are stored in JSON files in the annotations/progress_tracking/ directories. Applications Automated construction progress monitoring Scan-to-BIM comparison Scan-vs-BIM verification Object-level installation status assessment Digital twin updating 3. Processing Workflow The dataset supports a two-stage workflow for automated construction progress monitoring. In the first stage, semantic segmentation is used to extract the relevant target structure from the full scene point cloud. In the second stage, the extracted target point cloud is aligned with the corresponding planning model and analyzed at the component level to determine which planned elements are present in the scan data. Full Scene Point Cloud ↓Semantic Target Extraction ↓Target Point Cloud ↓Registration with Planning Model ↓Component-Level Verification ↓Construction Progress Assessment Synthetic point clouds generated from the planning models serve as idealized reference geometries for the component-wise comparison. 4. Planning Models and Synthetic Point Clouds The planning models were originally created from BIM data and converted into OBJ meshes. For every mesh, synthetic point clouds were generated. These synthetic point clouds provide idealized, noise-free representations of the planned geometries and serve as references for object verification. Advantages Known geometry No sensor noise Complete coverage Direct component correspondence 5. Real Scan Data The dataset includes real-world point clouds generated using multiple sensing technologies. Acquisition Methods Terrestrial laser scanning RIEGL VZ-400i Zeiss T-SCAN Image-based photogrammetry using Pix4D with images captured by an Apple iPad For each scene The dataset contains: Full scene point cloud Target-extracted point cloud Scene metadata 6. Annotation Data The dataset contains annotation files for two benchmark tasks: Semantic target extraction Object-level verification for construction progress monitoring Semantic Segmentation Labels Semantic segmentation labels are stored as plain text files in the annotations/scene_segmentation/ directory. Each file contains one semantic class label per line. Each semantic segmentation label file corresponds to the full scene point cloud stored in the scans/ directory. The i-th line in the label file contains the semantic class label of the i-th point in the corresponding full scene point cloud. The labels are therefore defined for the complete scene, including the target structure, the supporting ground surface, and all surrounding objects. The labels are not associated with the target-extracted point cloud. Label Definition Label ID Class Name Description 0 Environment All points outside the region of interest and its supporting ground 1 Ground The ground surface directly underlying the region of interest 2 Target All points belonging to the Object of Interest Example TargetTargetTargetGroundGroundEnvironmentEnvironmentEnvironment This means: Points 1 to 3 belong to the target structure. Points 4 to 5 belong to the ground. Remaining points belong to the environment. Object Verification Labels Object verification annotations are stored as JSON files in the annotations/progress_tracking/ directory. Each JSON file contains a list of planned components and their binary verification labels. Each entry consists of: source_file: path to the scanned target point cloud reference_file: path to the synthetic point cloud of a planned component ground_truth_class_object_verification: binary ground-truth label Label Definition Label ID Class Name Description 0 Object not verified The component could not be confirmed in the scan data 1 Object verified The component was successfully identified in the scan data Example Structure { "scene_008": [ { "source_file": "your_path/dataset/use_cases/uc_02_ioc_demonstrator/scans/scene_008/...building_extracted...ply", "reference_file": "your_path/dataset/use_cases/uc_02_ioc_demonstrator/synthetic_pointclouds/components/...IfcBeam...ply", "ground_truth_class_object_verification": 1 } ]} Label Map The file label_map.json defines the mapping between numeric label IDs and class names. This file ensures consistent label interpretation across all use cases and scenes. Annotation Workflow The annotation process follows two consecutive steps: Semantic Segmentation Separate the target structure from the complete scene. Assign each point to environment, ground, or target. Object Verification Compare each planned component with the registered scan data. Determine whether the component is verified (1) or not verified (0). This two-stage workflow mirrors the practical inspection process on construction sites: first isolate the building of interest, then inspect each planned component individually. 7. Dataset Contents The dataset contains the following data modalities. Data Type Format Description Planning models OBJ BIM-derived building meshes Synthetic point clouds PLY Noise-free reference point clouds Real point clouds PLY Captured scene and target point clouds Metadata JSON Acquisition and processing information Object verification labels JSON Component verification labels Semantic segmentation labels TXT Per-point semantic labels Utility scripts Python Visualization and preprocessing tools Documentation Markdown Technical documentation 8. Dataset Distribution and Folder Structure The dataset is distributed as a compressed ZIP archive named: IoC3D_v1.0.0.zip After extraction, the archive contains the complete dataset/ directory. dataset/├── README.md├── LICENSE├── label_map.json├── folder_structure.md├── dataset_description.json├── CITATION.cff├── utils/│ ├── outputs/├── use_cases/│ ├── uc_01_real_building_model_section/│ ├── uc_02_ioc_demonstrator/│ └── uc_03_steel_hall/└── docs/ Each use case contains: models/ synthetic_pointclouds/ scans/ annotations/ utils/ Python scripts for preprocessing, visualization, and annotation quality control. All generated outputs are written to: utils/outputs/ docs/ Supplementary documentation, including: File Description coordinate_system.md Coordinate conventions file_format_specification.md File format details annotation_guidelines.md Labeling instructions changelog.md Dataset version history Important Note The dataset structure and file names should not be modified. Several utility scripts automatically derive the locations of related files, such as annotations and planning models, from the predefined folder hierarchy. Renaming or moving files may therefore prevent the scripts from functioning correctly. 9. Utility Scripts The utils/ directory contains standalone Python GUI applications for visualization, preprocessing, and quality control of the dataset annotations. Current scripts include: ply_semantic_segmentation_class_splitter_and_colorizer_gui.py ply_object_knn_extractor_gui.py ply_object_verification_class_colorizer_gui.py These tools support: Semantic target extraction and annotation validation Object-level point cloud extraction Visualization of object verification labels All generated files are written to the utils/outputs/ directory. Each script creates its own output subdirectory, typically named after the processed scene or input file. The original dataset files are never modified. Important Folder Structure Requirement The original dataset folder structure and file names should not be modified. The utility scripts automatically infer the locations of related files, such as annotations, planning models, and synthetic point clouds, from the predefined dataset hierarchy. Renaming or moving files may therefore prevent the scripts from functioning correctly. Typical Workflow The utility scripts support the following processing sequence: Full Scene Point Cloud↓Semantic Segmentation Splitter↓Target Point Cloud↓Registration with Planning Model↓Component-Level Verification↓Construction Progress Assessment Together, these tools support annotation validation, debugging, and reproducible benchmark preparation. Companion GitHub Repository The latest version of the utility scripts, including installation instructions, detailed input and output descriptions, and usage examples, is available at: Construction3D-utils 10. Potential Research Applications IoC3D can be used for: Target extraction from construction scenes Scan-to-BIM registration Construction progress monitoring Semantic segmentation Change detection Digital twin updating Sensor fusion benchmarking Spatial AI for construction Object-level verification Scan-to-BIM alignment