PhD opportunities

Photo-realistic hybrid rendering of 3D point clouds for autonomous vehicle simulators

Thesis proposal

Area of expertiseReal-time computer science, robotics,systems and control - Paris
Doctoral SchoolSMI - Sciences des Mtiers de l'Ingnieur
SupervisorM. Franois GOULETTE
Co-supervisorM. Jean-Emmanuel DESCHAUD
Research unitMathematics and Systems
Starting dateOctober 1st 2019
KeywordsLIDAR, rendering, mobile mapping, photo-realistic, raytracing
AbstractThis thesis is related to the collaborative project REPLICA (with Renault, PSA) which aims to produce automatically 3D databases and a photo-realistic simulation of environments for the validation of autonomous vehicles.

The idea is to realistically simulate a set of sensors (camera, lidar, radar) from a 3D scene built entirely automatically from 3D point clouds and images. A stage of classification of the elements of the scene and distinction of the materials will be the work of another thesis upstream.

A first step will be to build a data structure capable of loading a large volume of data, containing the cloud of points, the normals and material information at each point allowing the re-illumination of the scene. Indeed, with the normal and even basic information on the bidirectional reflectance of the materials, it will be possible to modify the colors that were captured during the acquisition and to make them evolve with the displacement of the light sources or the sensors in the simulation.

A second step will be to adapt the principle of launching rays on point clouds (for example [LINSEN07] based on a splat representation of the point cloud). To reduce the calculation time and achieve real time, one solution will be to use graphics processors (GPU) instead of conventional processors (CPU) to benefit from their massively parallel processing capability.
ProfileGeneral profile:
Master level 2
Good interpersonal skills, rigor and autonomy
Writing and oral presentation skills
English spoken and written.
(For foreigners) French spoken and written.

Scientific and technological knowledge used:
3D data processing
Image processing
Synthesis of images
GPU programming
FundingConvention CIFRE
PDF documenthttps://www.adum.fr/script/downloadfile.pl?type=78&ID=25064