# Images and Point Clouds Cultural Heritage Dataset: Photogrammetric Images and 3D Point Clouds of Five Historic Buildings with Semantic Labels (HEIG-VD mirror)

## Facts

- Provider: Eugenio Pellis, Andrea Masiero, Michele Betti, Grazia Tucci, Pierre Grussenmeyer (original authors); HEIG-VD (mirror)
- License: CC-BY-4.0 (https://zenodo.org/api/records/14626611)
- Size: 6,510 files
- Format: PNG (in sampled files)
- Stored at: Hugging Face, https://huggingface.co/datasets/heig-vd-geo/ImagesAndPointCloudsCulturalHeritageDataset
- Access: public, readable without an account
- DOI: https://doi.org/10.5281/zenodo.14626611
- Category: Earth Observation & Geospatial
- Source: https://huggingface.co/datasets/heig-vd-geo/ImagesAndPointCloudsCulturalHeritageDataset
- Page: https://scigantic.com/archive/6af6ae22-5192-5543-a35d-948ce27c6148
- Keywords: Earth Observation & Geospatial, image segmentation, PNG, Hugging Face

## About

Photogrammetric images and 3D point clouds of five cultural heritage buildings, with semantic ground truth annotations for both the 2D images and the 3D points following the ARCHdataset architectural taxonomy (10 classes). The original release has five scene folders of about 35.5 GB with calibrated images, camera intrinsic and extrinsic parameters, point clouds and 2D and 3D labels, supporting 2D and 3D semantic segmentation, image to point cloud label transfer and multimodal fusion benchmarks for heritage building documentation and HBIM. This Hugging Face copy, kept by the HEIG-VD geomatics group, mirrors the five scene folders (1_SC, 2_OSA, 3_SS, 4_CG, 5_CB). The authoritative source is the Zenodo record by Eugenio Pellis, Andrea Masiero, Michele Betti, Grazia Tucci and Pierre Grussenmeyer, DOI 10.5281/zenodo.14626611, licensed CC BY 4.0. Cite the dataset and its paper.

## Load the data

```python
from huggingface_hub import hf_hub_download
path = hf_hub_download(repo_id="heig-vd-geo/ImagesAndPointCloudsCulturalHeritageDataset", filename="1_SC/1_Images/1_RGB/1_SC_001.png", repo_type="dataset")
print(path)
```

## Data structure

File types in sampled files: PNG

Example file: `1_SC/1_Images/1_RGB/1_SC_001.png`

## Open it

- In a hosted notebook with the data mounted: https://scigantic.com/archive/6af6ae22-5192-5543-a35d-948ce27c6148
- Full record as JSON (schema card included): https://api.scigantic.com/api/archives/6af6ae22-5192-5543-a35d-948ce27c6148
- Over MCP: `get_schema_card` with id `6af6ae22-5192-5543-a35d-948ce27c6148` at https://api.scigantic.com/mcp

## Related topics

- [Earth Observation & Geospatial datasets](https://scigantic.com/topics/earth-observation-and-geospatial)
- [Image segmentation datasets](https://scigantic.com/topics/image-segmentation)
- [PNG datasets](https://scigantic.com/topics/png)
