Point Cloud and 3D Modeling (NPM3D)
We created a website for Datasets and Benchmarks on 3D Point Clouds: https://npm3d.fr/
Research TOPIC NPM3D
NPM3D ("Nuage de Points et Modélisation 3D" in french) is a research topic in Centre for Robotics on 3D Point Clouds (from LiDAR and RGB-D sensors) and 3D Vision.
Main subjects of the NMP3D research topic are:
- Terrestrial mobile LiDAR systems
- LiDAR-only Simultaneous Localization And Mapping (SLAM)
- 3D Perception for autonomous systems (semantic segmentation, 3D detection)
- Deep Learning for 3D points clouds
- Point cloud rendering
- Surface reconstruction
People
Permanent staff:
- Jean-Emmanuel Deschaud: Full Professor (Directeur de Recherche HDR), Mines Paris - PSL, jean-emmanuel.deschaud@minesparis.psl.eu
External Collaborator:
- François Goulette: Full Professor, Deputy Director U2IS, ENSTA Paris, francois.goulette@ensta-paris.fr
PhD students:
- Alexandre Olech (2025-): Generative image-to-3D models with geometric and physical constraints. In collaboration with Santiago Velasco from STIM Lab.
- Wassil Lebsaira (2025-): Object digitization using radiance fields: acquisition, rendering, and evaluation with re-illumination on different types of displays. In collaboration with Alexis Paljic from CAOR Lab.
- Ugo Insalaco (2025-): Point cloud and image registration using differentiable rendering. In collaboration with Pierre Dellenbach from ChapsVision.
- Souheib Ben Mabrouk (2025-): 3D reconstruction, high quality rendering and stabilization from high resolution cameras. In collaboration with Nicolas Rahmouni from GoPro.
- Hugo Blanc (2022-): Physico-realistic differentiable rendering of point clouds for interactive visualization of real environments, and applications to cultural heritage. In collaboration with Alexis Paljic from CAOR Lab.
Former PhD students:
- Samir Abou-Haidar (2022-2025): Deep Neural Networks for 3D Point Cloud Semantic Segmentation Adapted to Embedded Computing Architectures for Mobile Autonomous and Robotic Systems (working now at SNCF Réseau as R&D engineer)
- Fabio Elnecave Xavier (2022-2025): Odometry and Local Elevation Mapping for Leg Exoskeletons with a Limited-FOV Depth Sensor (working now at Wandercraft as R&D engineer).
- Louis Soum-Fontez (2021-2025): LiDAR-based domain generalization and unknown 3D object detection (working now as Data Scientist at Pôle d'Expertise de la Régulation Numérique - PEReN).
- Jules Sanchez (2020-2023): Domain generalization for LiDAR data semantic segmentation for autonomous vehicles (working now at SNCF Réseau as R&D engineer).
- Pierre Dellenbach (2020-2023): Exploring LiDAR Odometries through Classical, Deep and Inertial perspectives (working now at ChapsVision Group as R&D engineer).
- Jean-Pierre Richa (2019-2022): Urban Scene Modeling From 3D Point Clouds and Massive LiDAR Simulation for Autonomous Vehicles (working now at Outsight as R&D engineer).
- Sofiane Horache (2019-2022): Pattern comparison on 3D point clouds and application on Celtic coins and objects (working now at TheraPanacea as R&D engineer).
- David Duque (2018-2021): 3D urban scene understanding by analysis of LiDAR, color and hyperspectral data (working now in the start-up Thecrossproduct as R&D engineer).
- Hugues Thomas (2016-2019): Learning new representations for 3D point cloud semantization (working now as Senior Research Engineer at Apple).
- Xavier Roynard (2015-2019): On-the-fly semantization of 3D point clouds acquired by embedded systems (working now at SAFRAN as R&D engineer).
- Hassan Bouchiba (2014-2018): Contributions in point-based processing for rendering and simulation in fluid mechanics (now co-founder of the start-up Exwayz).
- Houssem Nouira (2013-2016): Point cloud refinement with self-calibration of a mobile multi-beam lidar (working now at MENSI/TRIMBLE as R&D engineer).
TEACHING
Course on Point Cloud and 3D Modeling at Master 2 Paris-Saclay and Master 2 IASD PSL University: course website
PUBLICATIONS
2025
RayGaussX: Accelerating Gaussian-Based Ray Marching for Real-Time and High-Quality Novel View Synthesis
H. Blanc, J.-E. Deschaud, A. Paljic
ICCV, 2025
Paper arXiv Project Website Github
HARP-NeXt: High-Speed and Accurate Range-Point Fusion Network for 3D LiDAR Semantic Segmentation
S. Abou Haidar, A. Chariot, M. Darouich, C. Joly, J.-E. Deschaud
IROS, 2025
arXiv
HD-OOD3D: Supervised and Unsupervised Out-of-Distribution object detection in LiDAR data
L. Soum-Fontez, J.-E. Deschaud, F. Goulette
IROS, 2025
arXiv
RayGauss: Volumetric Gaussian-Based Ray Casting for Photorealistic Novel View Synthesis
H. Blanc, J.-E. Deschaud, A. Paljic
WACV, 2025
Paper arXiv Project Website Github
3DLabelProp: Geometric-Driven Domain Generalization for LiDAR Semantic Segmentation in Autonomous Driving
J. Sanchez, J.-E. Deschaud, F. Goulette
arXiv, 2025
arXiv
2024
Are We Ready for Real-Time LiDAR Semantic Segmentation in Autonomous Driving?
S. Abou Haidar, A. Chariot, M. Darouich, C. Joly, J.-E. Deschaud
IROS Workshop PPNIV, 2024
arXiv
2023
Multi-IMU Proprioceptive State Estimator for Humanoid Robots
F. Elnecave Xavier, G. Burger, M. Petriaux, J.-E. Deschaud, F. Goulette
IROS, 2023
Paper
2022
2021
On power Jaccard losses for semantic segmentation
D. Duque-Arias, S. Velasco-Forero, J.-E. Deschaud, F. Goulette, A. Serna, E. Decencière, B. Marcotegui
VISAPP, 2021
Paper
2020
SHREC 2020 Track: 3D Point Cloud Semantic Segmentation for Street Scenes
T. Ku, R. C. Veltkamp, B. Boom, D. Duque-Arias, S. Velasco-Forero, J.-E. Deschaud, F. Goulette, B. Marcotegui, S. Ortega, A. Trujillo, J. Pablo Suárez, J. Miguel Santana, C. Ramírez, K. Akadas, S. Gangisetty
Computer & Graphics, 2020
Paper
Computational Fluid Dynamics on 3D Point Set Surfaces
H. Bouchiba, S. Santoso, J.-E Deschaud, L. Rocha-Da-Silva, F. Goulette, T. Coupez
Journal of Computational Physics, 2020
Paper
2019
KPConv: Flexible and Deformable Convolution for Point Clouds
H. Thomas, C. R. Qi, J.-E. Deschaud, B. Marcotegui, F. Goulette, L. J. Guibas
ICCV, 2019
Paper GitHub TensorFlow GitHub PyTorch
A Graph-based Color Lines model for image analysis
D. Duque-Arias, S. Velasco-Forero, F. Goulette, J.-E. Deschaud, B. Marcotegui
ICIAP, 2019
Paper
2018
Semantic Classification of 3D Point Clouds with Multiscale Spherical Neighborhoods
H. Thomas, J.-E. Deschaud, B. Marcotegui, F. Goulette, Y. Le Gall
3DV, 2018
Paper
IMLS-SLAM: scan-to-model matching based on 3D data
J.-E. Deschaud
ICRA, 2018
Paper
2017
Point Cloud Refinement with Self-calibration of a mobile multi-beam Lidar Sensor
H. Nouira, J.-E. Deschaud, F. Goulette
The Photogrammetric Record, 2017
Paper
Current research projects
- PR[AI]RIE–PSAI PhD funding: https://www.prairie-psai.fr/
- ITN PhD funding: https://itn.dev/
- CIFRE thesis with ChapsVision (2025-2028): https://www.chapsvision.com/
- CIFRE thesis with GoPro (2025-2028): https://gopro.com/fr/fr/
PAST research projects
- CIFRE thesis with Wandercraft (2022-2025): bringing 3D vision to exoskeletons. Wandercraft Website
- European project 5GMed (H2020, 2021-2024): LiDAR object detection through 5G for railway cases. Project Website
- CIFRE thesis with Kitware (2021-2023): improving LiDAR SLAM. Kitware Website
- Research project with ANSYS (2020-2022): simulating LiDAR sensors with real LiDAR data. ANSYS Website
- FUI24 REPLICA Project (2018-2022) : The REPLICA project was on complement existing simulation platforms with new bricks in order to bridge the gap expected in autonomous vehicle testing.
SPONSORS
We want to thank the sponsors below:
Zulip is an open-source modern team chat app designed to keep both live and asynchronous conversations organized. Zulip Website