2018-00498 - Post-Doctoral Research Visit F/M [GRAPHDECO] Post-Doctoral Research Visit F/M on rendering with Uncertainty

Level of qualifications required : PhD or equivalent

Fonction : Post-Doctoral Research Visit

About the research centre or Inria department

The Inria Sophia Antipolis - Méditerranée center counts 37 research teams and 9 support departments. The center's staff (about 600 people including 400 Inria employees) is composed of scientists of different nationalities (250 foreigners of 50 nationalities), engineers, technicians and administrators. 1/3 of the staff are civil servants, the others are contractual. The majority of the research teams at the center are located in Sophia Antipolis and Nice in the Alpes-Maritimes. Six teams are based in Montpellier and a team is hosted by the computer science department of the University of Bologna in Italy. The Center is a member of the University and Institution Community (ComUE) "Université Côte d'Azur (UCA)".

Context

The goal of this postdoctoral fellowship is to rethink rendering algorithms by examining the inherent uncertainty of the input data and the rendering process itself. The topic is quite open and can focus either on examining uncertainty in "traditional" rendering algorithms (e.g., approximate global illumination) or on uncertainty in captured data (e.g., using geometry or materials captured from photographs or scanners), and algorithms such as image-based rendering (see our recent work [1-3]. Our methodology will be inspired by Uncertainty Quantification [4] and recent advances in machine learning [5].



Assignment

 

References


[1] Peter Hedman, Tobias Ritschel, George Drettakis, Gabriel Brostow
Scalable Inside-Out Image-Based Rendering, ACM Transactions on Graphics (SIGGRAPH Asia Conference Proceedings), Volume 35, Number 6 - December 2016 http://www-sop.inria.fr/reves/Basilic/2016/HRDB16/
[2] Rodrigo Ortiz-Cayon, Abdelaziz Djelouah, George Drettakis
A Bayesian Approach for Selective Image-Based Rendering using Superpixels
International Conference on 3D Vision (3DV) - 2015 http://www-sop.inria.fr/reves/Basilic/2015/ODD15/
[3] Gaurav Chaurasia, Sylvain Duchêne, Olga Sorkine-Hornung, George Drettakis Depth Synthesis and Local Warps for Plausible Image-based Navigation ACM Transactions on Graphics, Volume 32 - 2013 http://www-sop.inria.fr/reves/Basilic/2013/CDSD13/
[4] Ralph C Smith. Uncertainty quantification: theory, implementation, and applications, volume 12. Siam, 2013.
[5] Alex Kendall and Yarin Gal. What uncertainties do we need in Bayesian deep learning for computer vision? arXiv
preprint arXiv:1703.04977, 2017.

 

Main activities

The main responsibilities involve leading research projects on the defined topic, and projects in collaboration with Ph.D. students or supervising Masters interns.

Skills

Expertise in developing graphics systems in C++ and OpenGL is required, as well as knowledge of computer vision systems (e.g., OpenCV). Knowledge of machine learning is a strong plus. The working language is English, so the candidate must be fluent and have excellent writing and presentation skills.

Benefits package

  • Subsidised catering service
  • Partially-reimbursed public transport
  • Social security
  • Paid leave
  • Flexible working hours
  • Sports facilities

Remuneration

Gross Salary: 2650 brutto per month