Jean-Emmanuel Deschaud

Research Director

Center · CAOR

Email address: jean-emmanuel.deschaud@minesparis.psl.eu
Discipline(s): Signal, Image, Automatic Control, Robotics and Industrial Engineering
Topic(s): Robotics

Keywords

Awards & distinctions

2025 Best Paper Award à WACV 2025 pour l'article "RayGauss: Volumetric Gaussian-Based Ray Casting for Photorealistic Novel View Synthesis".
2022 Finalist for the "ICRA 2022 Outstanding Paper" award for the paper "CT-ICP: Real-time Elastic LiDAR Odometry with Loop Closure"; 3 papers were selected out of 1,498 submitted to the conference.
2021 Best Paper Award du Working Group on Graphics and Cultural Heritage 2021 pour l'article “Riedone3D: a celtic coins dataset for registration and fine-grained clustering”

Team

CAOR

Biography

Jean-Emmanuel Deschaud is a researcher at the Centre for Robotics at Mines Paris – PSL, specializing in 3D data processing and perception for autonomous systems. His work focuses on the use of LiDAR data for mobile robotics, autonomous vehicles, and heritage, particularly in semantic segmentation, mapping, and 3D modeling. He also develops methods for image-LiDAR registration, novel view synthesis, and surface reconstruction using photogrammetry. His research aims at robust, generalizable algorithms, adapted to embedded constraints when necessary, and to real, dynamic, and complex environments.

Publication(s)

2025
HARP-NeXt: High-Speed and Accurate Range-Point Fusion Network for 3D LiDAR Semantic Segmentation DOI : 10.1109/IROS60139.2025.11246557
2025
HD-OOD3D: Supervised and Unsupervised Out-of-Distribution object detection in LiDAR data DOI : 10.1109/IROS60139.2025.11247260
2025
RayGauss: Volumetric Gaussian-Based Ray Casting for Photorealistic Novel View Synthesis DOI : 10.1109/WACV61041.2025.00183
2025
COLA: COarse-LAbel Multisource LiDAR Semantic Segmentation for Autonomous Driving DOI : 10.1109/TRO.2025.3543302
2025
Leg Exoskeleton Odometry using a Limited FOV Depth Sensor DOI : 10.1109/ICRA55743.2025.11128659
2024
ParisLuco3D: A High-Quality Target Dataset for Domain Generalization of LiDAR Perception DOI : 10.1109/LRA.2024.3393209
2023
Multi-IMU Proprioceptive State Estimator for Humanoid Robots DOI : 10.1109/IROS55552.2023.10341849
2023
MDT3D: Multi-Dataset Training for LiDAR 3D Object Detection Generalization DOI : 10.1109/IROS55552.2023.10341614
2023
Domain generalization of 3D semantic segmentation in autonomous driving DOI : 10.1109/ICCV51070.2023.01657
2023
COLA: COarse LAbel pre-training for 3D semantic segmentation of sparse LiDAR datasets DOI : 10.1109/ICRA48891.2023.10160539
2023
5GMED Seamless Connectivity for Digital Trains DOI : 10.1109/VTC2023-Spring57618.2023.10199954
2022
AdaSplats: Adaptive Splatting of Point Clouds for Accurate 3D Modeling and Real-Time High-Fidelity LiDAR Simulation DOI : 10.3390/rs14246262
2022
CT-ICP: Real-time Elastic LiDAR Odometry with Loop Closure DOI : 10.1109/ICRA46639.2022.9811849
2021
Paris-carla-3d: A real and synthetic outdoor point cloud dataset for challenging tasks in 3d mapping DOI : 10.3390/rs13224713
2021
3D Point Cloud Registration with Multi-Scale Architecture and Unsupervised Transfer Learning DOI : 10.1109/3DV53792.2021.00142
2021
What's in My LiDAR Odometry Toolbox DOI : 10.1109/IROS51168.2021.9636348
2021
On power jaccard losses for semantic segmentation
2020
SHREC 2020: 3D point cloud semantic segmentation for street scenes DOI : 10.1016/j.cag.2020.09.006
2020
Automatic Clustering of Celtic Coins Based on 3D Point Cloud Pattern Analysis DOI : 10.5194/isprs-annals-V-2-2020-973-2020
2020
Computational fluid dynamics on 3D point set surfaces DOI : 10.1016/j.jcpx.2020.100069
2019
KPConv: Flexible and deformable convolution for point clouds DOI : 10.1109/ICCV.2019.00651
2019
A graph-based color lines model for image analysis DOI : 10.1007/978-3-030-30645-8_17
2018
Paris-lille-3D: A point cloud dataset for urban scene segmentation and classification DOI : 10.1109/CVPRW.2018.00272
2018
IMLS-SLAM: Scan-to-Model Matching Based on 3D Data DOI : 10.1109/ICRA.2018.8460653
2018
Semantic classification of 3d point clouds with multiscale spherical neighborhoods DOI : 10.1109/3DV.2018.00052
2018
Paris-Lille-3D: A large and high-quality ground-truth urban point cloud dataset for automatic segmentation and classification DOI : 10.1177/0278364918767506
2018
EDITORIAL DOI : 10.52638/rfpt.2018.423
2018
Editorial; [Editorial]
2018
Raw point cloud deferred shading through screen space pyramidal operators DOI : 10.2312/egs.20181036
2017
Point cloud refinement with self-calibration of a mobile multibeam lidar sensor DOI : 10.1111/phor.12198
2017
High quality and efficient direct rendering of massive real-world point clouds DOI : 10.2312/egp.20171035
2017
Automatic Ground Surface Reconstruction from mobile laser systems for driving simulation engines DOI : 10.1177/0037549716683022
2016
Point cloud refinement with a target-free intrinsic calibration of a mobile multi-beam Lidar system DOI : 10.5194/isprsarchives-XLI-B3-359-2016
2016
Fast and robust segmentation and classification for change detection in urban point clouds DOI : 10.5194/isprsarchives-XLI-B3-693-2016
2016
Experimental assessment of the quanergy M8 LiDAR sensor DOI : 10.5194/isprsarchives-XLI-B5-527-2016
2015
Invariant EKF Design for Scan Matching-Aided Localization DOI : 10.1109/TCST.2015.2413933
2015
Target-free extrinsic calibration of a mobile multi-beam lidar system DOI : 10.5194/isprsannals-II-3-W5-97-2015
2014
Scalable and detail-preserving ground surface reconstruction from large 3D point clouds acquired by mobile mapping systems DOI : 10.5194/isprsarchives-XL-3-73-2014
2014
Experimental implementation of an Invariant Extended Kalman Filter-based scan matching SLAM DOI : 10.1109/ACC.2014.6859291
2014
Paris-rue-madame database: A 3D mobile laser scanner dataset for benchmarking urban detection, segmentation and classification methods DOI : 10.5220/0004934808190824
2012
3D road environment modeling applied to visibility mapping: An experimental comparison DOI : 10.1109/DS-RT.2012.12
2012
3D Mapping for high-fidelity unmanned ground vehicle lidar simulation DOI : 10.1177/0278364912460288
2012
Automatic data driven vegetation modeling for lidar simulation DOI : 10.1109/ICRA.2012.6225269
2011
A simple nonlinear filter for low-cost ground vehicle localization system DOI : 10.1109/CDC.2011.6161262
2010
Point cloud non local denoising using local surface descriptor similarity
2009
Colorisation et texturation temps reel d'environnements urbains par systeme mobile avec scanner laser et camera fish-eye
2007
On-the-way city mobile mapping using laser range scanner and fisheye camera

Teaching

Point clouds and 3D modeling

2014 – en cours Course Director

This course provides an overview of the concepts and techniques for acquiring, processing, and visualizing 3D point clouds, as well as their mathematical and algorithmic foundations.

PhD supervision

2025 3D reconstruction, high-quality rendering, and stabilization from high-resolution cameras BEN MABROUK Souheib
2025 Point cloud and image registration via differentiable rendering INSALACO Ugo
2025 3D Generative Models with Geometric Constraints OLECH Alexandre
2025 Digitization of objects using radiance fields: acquisition, rendering, and evaluation with relighting on different types of displays LEBSAIRA Wassil
2022 Odometry and local elevation maps for leg exoskeletons with a limited field-of-view depth sensor ELNECAVE XAVIER Fabio
2022 Deep neural networks for semantic segmentation of 3D point clouds adapted to embedded architectures for autonomous mobile and robotic systems ABOU HAIDAR Samir
2022 Realistic differentiable rendering of point clouds for interactive visualization of real environments. Applications to cultural heritage for the study of archaeological objects and virtual visits of monuments. BLANC Hugo
2021 Generalization of domain and 3D detection of unknown objects from LiDAR data SOUM-FONTEZ Louis
2020 Exploration of LiDAR odometry through classical, deep learning, and inertial perspectives DELLENBACH Pierre
2020 Generalization of domain for semantic segmentation of LiDAR data for autonomous vehicles SANCHEZ Jules
2019 Comparison of patterns on 3D point clouds and application to Celtic coins and artifacts HORACHE Sofiane
2019 Urban scene modeling from 3D point clouds and massive LiDAR simulation for autonomous vehicles RICHA Jean Pierre
2018 3D urban scene understanding through LiDAR, color, and hyperspectral data analysis DUQUE David
2016 Learning new representations for the semantic enrichment of 3D point clouds THOMAS Hugues
2015 On-the-Fly Semantization of 3D Point Clouds Acquired by Embedded Systems ROYNARD Xavier