heig-vd-geo/ImagesAndPointCloudsCulturalHeritageDataset

---
license: cc-by-4.0
task_categories:
- image-segmentation
language:
- en
pretty_name: Images & Point Clouds Cultural Heritage Dataset
---

# Images & Point Clouds Cultural Heritage Dataset

This repository provides a **mirror of the Images & Point Clouds Cultural Heritage Dataset** to facilitate access for research and benchmarking purposes.

> ⚠️ **Disclaimer**
> This dataset is **not owned nor created by the maintainer of this Hugging Face repository**.
> The **official and authoritative source** is the original Zenodo record:
> https://zenodo.org/records/14626611

---

## Dataset Description

The dataset contains **photogrammetric images and 3D point clouds of five cultural heritage buildings**, with **semantic ground truth annotations** for both modalities.

It supports:
- 2D and 3D semantic segmentation
- Image–point cloud fusion
- Multi-modal learning and benchmarking in cultural heritage scenarios

Annotations follow the **ARCHdataset semantic taxonomy** (10 classes).

---

## Data Content

The original dataset consists of five scene-level folders, totaling approximately **35.5 GB**, and includes:
- Calibrated photogrammetric images
- Camera intrinsic and extrinsic parameters
- 3D point clouds
- 2D and 3D semantic annotations

Please refer to the Zenodo record for detailed structure and acquisition information.

---

## Citation

If you use this dataset in academic work, **please cite both the dataset and the associated publication**.

### Dataset (Zenodo)

```bibtex
@dataset{pellis_images_pointclouds_2025,
author = {Pellis, Eugenio and Masiero, Andrea and Betti, Michele and Tucci, Grazia and Grussenmeyer, Pierre},
title = {Images\&PointClouds Cultural Heritage Dataset},
year = {2025},
publisher = {Zenodo},
doi = {10.5281/zenodo.14626611},
url = {https://doi.org/10.5281/zenodo.14626611}
```

### Associated publication

```bibtex
@article{pellis2025photogrammetric,
author = {Pellis, Eugenio and Masiero, Andrea and Betti, Michele and Tucci, Grazia and Grussenmeyer, Pierre},
title = {A photogrammetric image-point dataset for the semantic segmentation of heritage building},
journal = {Data in Brief},
year = {2025},
volume = {60},
doi = {10.1016/j.dib.2025.111661}
}
```

## License

This dataset is released under the Creative Commons Attribution 4.0 International (CC BY 4.0) license.

Use, redistribution, and adaptation are permitted provided appropriate credit is given to the original authors.

## Links

- Official Zenodo record: https://zenodo.org/records/14626611
- Dataset DOI: https://doi.org/10.5281/zenodo.14626611
- Publication DOI: https://doi.org/10.1016/j.dib.2025.111661