Synthetic Dataset for Point Cloud Semantic Segmentation

The Synthetic Point Cloud Dataset is made of point clouds derived from existing 3D models and is composed by two parts. The first includes points clouds extracted from 3D models of real historical buildings. The second part includes point clouds derived from a collection of 3D objects of single architectural elements, harvested from open online repositories.

To obtain this dataset, as well as the implementation code, we ask you to complete, sign and return the form below. After that, I will send you the credentials to download it. Note that the dataset is available only for research purposes.

  • Fill out this form: request form
  • Send it to: (Note: you should send the email from an email address that is linked to your research institution/university)
  • Wait for the credentials
  • You will be sent a link for the download.