# A photogrammetric image-point dataset for the semantic segmentation of heritage buildings

## TL;DR

This paper introduces a dataset for 3D modeling of historic buildings, combining images and point clouds with semantic labels to improve automation in scan-to-BIM workflows.

## Contribution

The novelty lies in providing a manually annotated photogrammetric dataset with aligned images and point clouds for semantic segmentation of heritage buildings.

## Key findings

- The dataset includes five historic buildings with georeferenced point clouds and images.
- Semantic labels for 10 construction elements are provided for both images and point clouds.
- Camera parameters and alignment matrices are included to facilitate accurate modeling.

## Abstract

In this article, we present a new dataset designed for the semantic segmentation of images and point clouds of historic buildings, aimed at automating and accelerating the 3D modeling process in the scan-to-BIM context. The dataset includes five historic buildings and provides two types of data: images obtained from photogrammetric surveys and the corresponding georeferenced point clouds. Both datasets are accompanied by ground truth, identifying 10 classes representative of the main construction elements. Additionally, the dataset includes the intrinsic and extrinsic camera parameters and the transformation matrix to align the point clouds with the camera reference system. The annotation of the point clouds was performed manually, while the image annotation was generated through a projection process based on the labels assigned to the point clouds.