3DSES: An Indoor Lidar Point Cloud Segmentation Dataset with Real and Pseudo-Labels from a 3D Model

Maxime Mérizette, Maxime Mérizette, Maxime Mérizette, Nicolas Audebert, Nicolas Audebert, Pierre Kervella, Pierre Kervella, Jérôme Verdun

2025

Abstract

Semantic segmentation of indoor point clouds has found various applications in the creation of digital twins for robotics, navigation and building information modeling (BIM). However, most existing datasets of labeled indoor point clouds have been acquired by photogrammetry. In contrast, Terrestrial Laser Scanning (TLS) can acquire dense sub-centimeter point clouds and has become the standard for surveyors. We present 3DSES (3D Segmentation of ESGT point clouds), a new dataset of indoor dense TLS colorized point clouds covering 427 m2 of an engineering school. 3DSES has a unique double annotation format: semantic labels annotated at the point level alongside a full 3D CAD model of the building. We introduce a model-to-cloud algorithm for automated labeling of indoor point clouds using an existing 3D CAD model. 3DSES has 3 variants of various semantic and geometrical complexities. We show that our model-to-cloud alignment can produce pseudolabels on our point clouds with a > 95% accuracy, allowing us to train deep models with significant time savings compared to manual labeling. First baselines on 3DSES show the difficulties encountered by existing models when segmenting objects relevant to BIM, such as light and safety utilities. We show that segmentation accuracy can be improved by leveraging pseudo-labels and Lidar intensity, an information rarely considered in current datasets. Code and data will be open sourced.

Paper Citation

in Harvard Style

Mérizette M., Audebert N., Kervella P. and Verdun J. (2025). 3DSES: An Indoor Lidar Point Cloud Segmentation Dataset with Real and Pseudo-Labels from a 3D Model. In Proceedings of the 20th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 2: VISAPP; ISBN 978-989-758-728-3, SciTePress, pages 707-716. DOI: 10.5220/0013237300003912

in Bibtex Style

@conference{visapp25,
author={Maxime Mérizette and Nicolas Audebert and Pierre Kervella and Jérôme Verdun},
title={3DSES: An Indoor Lidar Point Cloud Segmentation Dataset with Real and Pseudo-Labels from a 3D Model},
booktitle={Proceedings of the 20th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 2: VISAPP},
year={2025},
pages={707-716},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0013237300003912},
isbn={978-989-758-728-3},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 20th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 2: VISAPP
TI - 3DSES: An Indoor Lidar Point Cloud Segmentation Dataset with Real and Pseudo-Labels from a 3D Model
SN - 978-989-758-728-3
AU - Mérizette M.
AU - Audebert N.
AU - Kervella P.
AU - Verdun J.
PY - 2025
SP - 707
EP - 716
DO - 10.5220/0013237300003912
PB - SciTePress