caor@mines-paristech.fr

Nuage de Points et Modélisation 3D (NPM3D)

                                                             

 

We created NPM3D Benchmark Suite on 3D Point Clouds: http://npm3d.fr/

If you are interested for internship or thesis in our team, you can contact jean-emmanuel.deschaud@mines-paristech.fr or francois.goulette@mines-paristech.fr

 


Research Team NPM3D

 

Research areas of the NMP3D team are around 3D data as « point cloud »:

 – Mobile LiDAR systems
 – Point cloud rendering (screen-space rendering, splatting)
 – LiDAR SLAM, Localization on Map
 – HD Maps for autonomous vehicles
 – Point Cloud processings from archeological sites / objects
 – Object recognition / scene segmentation and classification in LiDAR data
 – Deep Learning for 3D Point Clouds

We have multiple 3D sensors (Kinect 2, scanner FARO Focus X130, Velodyne VLP16, HDL32) and two mobile mapping platforms:
 – L3D2: vehicle with GPS/IMU localization system, Velodyne HDL32 and Ladybug5
 – Drone with Velodyne VLP16 and Camera FLIR Blackfly

 


People

 

 • Researchers:
       – François Goulette: Full Professor, francois.goulette@mines-paristech.fr
       – Jean-Emmanuel Deschaud: Associate Professor, jean-emmanuel.deschaud@mines-paristech.fr

 • PhD students:
       – Hugues Thomas (2016-): Learning new representations for 3D point cloud semantization
       – Xavier Roynard (2015-): Semantization of 3D Points Clouds acquired by Embedded System

 • Former PhD students:
       – Hassan Bouchiba (2014-2018): Contributions in point-based processing for rendering and simulation in fluid mechanics (working now at Terra3D)
       – Houssem Nouira (2013-2016): Point cloud refinement with self-calibration of a mobile multi-beam lidar (working now at MENSI/TRIMBLE)

 


Selected Papers

 

IROS2018

 

 

Classification of Point Cloud for Road Scene Understanding with Multiscale Voxel Deep Network, Workshop IROS, October 2018, pdf

 

 

 

3DV2018

 

Semantic Classification of 3D Point Clouds with Multiscale Spherical Neighborhoods, 3DV, September 2018, pdf

 

 

 

 

Eurographics2018

 

Raw point cloud deferred shading through screen space pyramidal operators, Short Paper EUROGRAPHICS, April 2018, video, pdf 

 

 

 

ICRA2018

 

 

 

 

IMLS-SLAM: scan-to-model matching based on 3D data, ICRA, May 2018, pdf

 

 

 

 

 

 Record2017

 

 

Point Cloud Refinement with Self-calibration of a mobile multi-beam Lidar Sensor, The Photogrammetric Record, September 2017, pdf

 

 

 

 

 


Current research projects

 

REPLICA

 

 

REPLICA : Automated massive computing platform for autonomous vehicle with realistic sensors simulation 

 

 

 

 

 ARCHEO3D

 

ARCHEO 3D : Exploitation of new laser imaging techniques for non-destructive archeology: reconstruction of surfaces of celtic objects

 

 

 

 

 


Start-up Terra3D

 

 terra3d_railway

 

A start-up based on the research work of the NPM3D team has been created in October 2015 : Terra3D

 

 

 


Teaching

 

 • Course on 3D Point Clouds in the Master 2 MVA at ENS Paris-Saclay: course webpage here

 • Course on Vision for Robotics in the Master 2 Informatique at UPMC

 


If you do not know « 3D Point Cloud data »

 

cour_bordure

 

 

Point Cloud of MINES ParisTech (FARO Focus X130)

 

 

 

FacadeMINES_contour

 

 

Point Cloud of MINES ParisTech (FARO Focus X130)

 

 

 

Lille_contour

 

 

 Point Cloud of the city of Lille (our plateform L3D2 with Velodyne HDL32)