IRIS-v2

An Industrial Dataset for
Scene Acquisitions and Functional Schematics Alignment

Flavien Armangeon1,2, Thibaud Ehret1, Enric Meinhardt-Llopis1 Rafael Grompone Von Gioi1, Guillaume Thibault2, Marc Petit2, Gabriele Facciolo1,
1Université Paris-Saclay, CNRS, ENS Paris-Saclay, Centre Borelli, France 2EDF R&D (Electricité de France), France
arXiv IRIS Dataset Code (coming soon)

Abstract

Aligning functional schematics with 2D and 3D scene acquisitions is crucial for building digital twins, especially for old industrial facilities that lack native digital models. Current manual alignment using images and LiDAR data does not scale due to tediousness and complexity of industrial sites. Inconsistencies between schematics and reality, and the scarcity of public industrial datasets, make the problem both challenging and underexplored. This paper introduces IRIS-v2, a comprehensive dataset to support further research. It includes images, point clouds, 2D annotated boxes and segmentation masks, a CAD model, 3D pipe routing information, and the P&ID (Piping and Instrumentation Diagram). The alignment is experimented on a practical case study, aiming at reducing the time required for this task by combining segmentation and graph matching.

BibTeX

If you use this work in your research, please use the following BibTeX entries.


@article{armangeon2026irisv2,
    title={An Industrial Dataset for Scene Acquisitions and Functional Schematics Alignment}, 
    author={Flavien Armangeon and Thibaud Ehret and Enric Meinhardt-Llopis and Rafael Grompone von Gioi and Guillaume Thibault and Marc Petit and Gabriele Facciolo},
    journal={arXiv:2602.15584},
    year={2026}
}

@INPROCEEDINGS{10943543,
    author={Armangeon, Flavien and Ehret, Thibaud and Meinhardt-Llopis, Enric and Von Gioi, Rafael Grompone and Thibault, Guillaume and Petit, Marc and Facciolo, Gabriele},
    booktitle={2025 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, 
    title={IRIS-VIS: A New Dataset for Visibility Estimation in an Industrial Environment}, 
    year={2025},
    volume={},
    number={},
    pages={7235-7243},
    keywords={Point cloud compression;Measurement;Computer vision;Surface reconstruction;Solid modeling;Three-dimensional displays;Laser radar;Statistical analysis;Shape;Estimation;dataset;point cloud;visibility estimation;cad model;industrial;indoor},
    doi={10.1109/WACV61041.2025.00703}
}

@dataset{armangeon_2025_13777859,
    author       = {Armangeon, Flavien and
                    Ehret, Thibaud and
                    Meinhardt-Llopis, Enric and
                    Grompone Von Gioi, Rafael and
                    Thibault, Guillaume and
                    Petit, Marc and
                    Facciolo, Gabriele},
    title        = {IRIS: Industrial Room In Saclay},
    month        = feb,
    year         = 2025,
    publisher    = {EDF (Électricité de France)},
    version      = {1.0},
    doi          = {10.5281/zenodo.13777859},
    url          = {https://doi.org/10.5281/zenodo.13777859},
}