Thibault GROUEIX
thibault dot groueix dot 2012 at polytechnique dot org

I am a second year PhD student in the Imagine group, part of the Laboratoire d'Informatique Gaspard-Monge of the Ecole Nationale des Ponts et Chaussées . My current research interests range from Deep Learning, to Computer Graphics.

My advisors are Mathieu AUBRY, and Renaud MARLET. My PhD is funded by the Université Paris-Est-Marne-la-Vallée and Ecole Nationale des Ponts et Chaussées. I've spent time at Telecom ParisTech 3D computer graphics group, and at the EPFL Biomedical Imaging Group. I graduated from Ecole Polytechnique.

CV                           Github                 Scholar

news
  • August 2018: Invited speaker at the 4th International Workshop on Recovering 6D Object Pose. [Slides]
  • July 2018:3D-CODED is accepted at ECCV
  • July 2018: Going to summer school PAISS : -> BEST POSTER AWARD ! :-)
  • February-June 2018 : Teaching some TPs of MALAP and TIVA, M1 courses at ENPC.
  • March 2018: ECCV submission :)
  • March 2018: Our paper is accepted as a spotlight at CVPR
  • November 2017: CVPR submission :)
  • July-September 2017: Summer Internship at Adobe .
  • February-June 2017: Teaching some TPs of MALAP and TIVA, M1 courses at ENPC.
  • December 2016: I am starting my PhD.
research

Currently working on 3D GANS.

3D-CODED : 3D Correspondences by Deep Deformation ~NEW~ ECCV
T. Groueix, M. Fisher, V. G. Kim, B. C. Russell, M. Aubry
IMAGINE team, Ecole des Ponts ParisTech -- Adobe Research
pdf | webpage

Given two input shapes without vertex correspondences, the goal is to establish correspondences between them. To do so, we learn a smooth deformation transforming a template shape into the input shape. The two reconstructions are naturally in correspondences, as they span from two different deformations of the same template.

AtlasNet: A Papier-Mâché Approach to Learning 3D Surface Generation ~NEW~ CVPR spotlight , Best Poster Award at P.R.A.I.R.I.E. Artificial Intelligence Summer School
T. Groueix, M. Fisher, V. G. Kim, B. C. Russell, M. Aubry
IMAGINE team, Ecole des Ponts ParisTech -- Adobe Research
pdf | webpage | Adobe Blogpost

3D Synthesis : Instead of generating point clouds or voxels, AtlasNet directly generates meshes at arbitrary resolution. It has strong advantages : generalization capabilities, morphing, co-segmentation, regular texture parameterization. We demonstrate its strenght on an autoencoder, and single-view reconstruction from one still image.

Interactive Monte-Carlo Ray-Tracing Upsampling
M. Boughida, T. Groueix, T. Boubekeur
Eurographics Poster, 2016
abstract | poster | slide

Approximate real-time previzualition of Global Illumination (GI) relying on NVIDIA Optix (parallelized ray tracing). To approximate GI in real time, we apply a Joint Bilateral Filter on a sub-sampled rendered image and a high-resolution G-buffer (containing depth, normal, and albedo).

thesis

Photorealist Synthetic Images For Deep Learning
Thibault GROUEIX
Advisors: Prof. Mathieu Aubry - Prof. Renaud Marlet
IMAGINE team - Ecole des Ponts ParisTech

teaching
teach

Cours apprentissage statistique (MALAP), parcours IMI, Ecole des Ponts-ParisTech
Spring 2018, Spring 2017
Lab Assistant (LA)

teach

Traitement de l'information et vision artificielle (TIVA), parcours IMI, Ecole des Ponts-ParisTech
Spring 2018, Spring 2017
Lab Assistant (LA)

codedemo

All of my released code is hosted on my GitHub account. Long live the open-source community in ML !


I really like this website. Learned a lot from here too.