2022-05142 - PhD Position F/M Generative Models for Neural Rendering
Le descriptif de l’offre ci-dessous est en Anglais

Type de contrat : CDD

Niveau de diplôme exigé : Bac + 5 ou équivalent

Fonction : Doctorant

A propos du centre ou de la direction fonctionnelle

The Inria Sophia Antipolis - Méditerranée center counts 34 research teams as well as 7 support departments. The center's staff (about 500 people including 320 Inria employees) is made up of scientists of different nationalities (250 foreigners of 50 nationalities), engineers, technicians and administrative staff. 1/3 of the staff are civil servants, the others are contractual agents. The majority of the center’s research teams are located in Sophia Antipolis and Nice in the Alpes-Maritimes. Four teams are based in Montpellier and two teams are hosted in Bologna in Italy and Athens. The Center is a founding member of Université Côte d'Azur and partner of the I-site MUSE supported by the University of Montpellier.

Contexte et atouts du poste

The Ph.D. thesis will take place at the GRAPHDECO group (http://team.inria.fr/graphdeco) at Inria Sophia Antipolis.



Mission confiée

This Ph.D. will investigate generative models for neural rendering in computer graphics, both for captured and synthetic scenes. Recent work has seen an explosion in neural rendering techniques based on Neural Fields; however, these methods tend to overfit a single scene [1], making any kind of modification or manipulation very hard. Recent results combining Neural Field Rendering and GANs [2] show a promising avenue of research where the power and expressivity of each can be combined to allow the creation of Neural Representations that are easily to modify and manipulate. We will build on initial results developed in the context of the ERC FUNGRAPH, starting with stochastic structures for 3D textures, then specializing towards more complex categories of scenes (e.g., cars, or specific categories of indoor rooms). Our first results that build on approaches similar to [2] are very promising, both for real and synthetic data; however manipulating real data in a disentangled manner is still very challenging.  We will focus on effective training strategies, in the spirit of our previous work (see https://project.inria.fr/fungraph/publications/), possibly combining synthetic or multi-view data with "data in the wild" typically used for GANs, on different ways to extract the generative Neural Field models so they can become usable first-class 3D assets and on novel approaches to editing and manipulating these generative Neural Fields.


[1] Tewari A, Thies J, Mildenhall B, Srinivasan P, Tretschk E, Yifan W, Lassner C, Sitzmann V, Martin‐Brualla R, Lombardi S, Simon T. Advances in neural rendering. InComputer Graphics Forum 2022 May (Vol. 41, No. 2, pp. 703-735).

[2] Chan ER, Lin CZ, Chan MA, Nagano K, Pan B, De Mello S, Gallo O, Guibas LJ, Tremblay J, Khamis S, Karras T. Efficient geometry-aware 3D generative adversarial networks. InProceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition 2022 (pp. 16123-16133).


Principales activités

The main activities will involve research in the topic of generative rendering algorithms for computer graphics.


Candidates should have an M.Sc. in Computer Graphics or Computer vision, with expertise in both. A suitable candidate will have strong programming and mathematical skills as well as knowledge in computer graphics, geometry processing and machine learning, with experience in C++, OpenGL and GLSL on the graphics side, and tensorflow/pytorch for learning.


  • 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
  • Supplementary social protection


Duration: 36 months
Location: Sophia Antipolis, France
Gross Salary per month: 2051€ per month (year 1 & 2) and 2158€ per month (year 3)