2020-02984 - PhD Position F/M PhD on 3D Scene Understanding for Autonomous Driving

Contract type : Fixed-term contract

Level of qualifications required : Graduate degree or equivalent

Fonction : PhD Position

Level of experience : Recently graduated


In the context of a French research project including other academicals and industrials we are looking for a very good PhD student on 3D scene understanding from Image and Lidar data for autonomous driving applications.

The job is located in center of Paris (France), at the Inria national research institute RITS team (Robotics and Intelligent Transportation System). The team has approx. 20 people working on Computer Vision/Planning/Control for intelligent transportation and autonomous vehicles (to test/validate our researches). The environment is nice and lively, with people from worldwide origins. Social skills will be appreciated, as collaborations with other researchers/PhDs is expected. 


The candidate will research on 3D vision and will propose new algorithms and methodology to provide 3D scene understanding. Of importance, outdoor mobile robotics must observe and sense their environment accurately to take wise decisions. While earlier researches were processing 2D vision (object detection, semantic segmentation, etc.) recent deep networks are now able to handle 3D data and to reason in 3D to solve the same tasks directly in the 3D world referential. The candidate will have first to study the literature and master the existing techniques relying on voxel based or point based representations. During the PhD, it is intended for the candidate to propose new ideas and research directions.

While the project framework is rather flexible and allows a variety of works, we intend to tackle some of the followings: 3D semantic completion, 3D semantic segmentation, 3D odometry, 3D geometry reconstruction, etc. In a second part of the PhD we propose to extend the work to semi-supervised or unsupervised techniques so as to address domain adaptation and overcome the limitation of fully supervised techniques.

The applications will necessarily include autonomous driving but might extend to a wide range of other applications (virtual/augmented reality, entertainment, etc.). Of interest, the team has real working prototypes and the student could (but not mandatory) include some real experiments.

Main activities

See above



Benefits package

  • Subsidized meals
  • Partial reimbursement of public transport costs
  • Leave: 7 weeks of annual leave + 10 extra days off due to RTT (statutory reduction in working hours) + possibility of exceptional leave (sick children, moving home, etc.)
  • Possibility of teleworking (after 6 months of employment) and flexible organization of working hours
  • Professional equipment available (videoconferencing, loan of computer equipment, etc.)
  • Social, cultural and sports events and activities
  • Access to vocational training
  • Social security coverage