ModelMine: Large scale 3D model housing database for Architecture design

ModelMine is a curated research dataset designed to support machine learning, computer vision, and generative modeling research in architecture, housing, and spatial design.

The dataset brings together structured representations of residential architecture across diverse styles, geographies, and design paradigms, with the goal of enabling data-driven approaches to architectural analysis, synthesis, and education.

How to Acess ModelMine Dataset

Due to dataset size, licensing considerations, and the need for controlled distribution, ModelMine is not directly hosted on Zenodo.

The dataset is distributed via Kaggle using a private dataset configuration.

How to Request Access

Researchers and practitioners may request access by providing:

Their Kaggle username

Institutional or organizational affiliation

A brief description of intended use

Access requests must be sent to: [e-mail] or [e-mail]

Approved users will be granted access by being added as collaborators to the private Kaggle dataset.

Canonical Record, Versioning, and Citation

Zenodo serves as the canonical, citable record for ModelMine.

The Kaggle dataset mirrors the files corresponding to the latest Zenodo release.

If you use ModelMine in academic publications or derivative work, please cite this Zenodo record using the DOI provided on this page.The Zenodo-provided citation formats (BibTeX, APA, etc.) should be preferred over citing the Kaggle mirror.

License

ModelMine is released under the Creative Commons Attribution 4.0 International (CC BY 4.0) license.Users may share and adapt the dataset for research and educational purposes, provided appropriate attribution is given.