Thibault GROUEIX
thibault.groueix.2012 at polytechnique.org

Bio. I joined Adobe Research in April 2021.

My research interests are centered around Deep Learning, Computer Graphics and 3D shape analysis.

I am an alumni from the Imagine group, Ecole des Ponts. I've also spent time with great teams : Naver Labs Europe, Telecom ParisTech, and EPFL. (Last update: April 2021)

news
research

Deep Transformation-Invariant Clustering Neurips 2020 Oral
T. Monnier , T. Groueix , M. Aubry
IMAGINE team, Ecole des Ponts ParisTech
Paper | Webpage | Code | Bibtex

We propose two gradient-based deep methods to perform an image clustering invariant to spatial, color and morphological transformations. We showcase its robustness and interpretability by visualizing clustering results over real photograph collections and instagram hashtags.

@inproceedings{monnier2020dticlustering,
  title={Deep Transformation-Invariant Clustering},
  author={Monnier, Tom and Groueix, Thibault and Aubry, Mathieu},
  booktitle={arXiv:2006.11132},
  year={2020}
}
              

Learning elementary shape structures Neurips 2019
T. Deprelle , T. Groueix, M. Fisher, V. G. Kim , B. C. Russell, M. Aubry
IMAGINE team, Ecole des Ponts ParisTech -- Adobe Research
Paper | Webpage | Code | Bibtex

A combination of learned elementary 3D structures are used to represent 3D shapes. The learned elementary 3D structures are highly interpretable and lead to clear improvements in 3D shape generation and matching.

@inproceedings{deprelle2019learning,
  title={Learning elementary structures for 3D shape generation and matching},
  author={Deprelle, Theo and Groueix, Thibault and Fisher, Matthew and Kim, Vladimir G and Russell, Bryan C and Aubry, Mathieu},
  booktitle={Neurips},
  year={2019}
}
              

Unsupervised cycle-consistent deformation for shape matching SGP 2019
T. Groueix, , M. Fisher, V. G. Kim , B. C. Russell, M. Aubry
IMAGINE team, Ecole des Ponts ParisTech -- Adobe Research
Paper | Webpage | Slides | Code | Bibtex

We propose a solution to the task of putting objects of arbitrary topologies in correspondences. Matching can be solved by predicting dense deformations. In this work, we introduce a deep learning method to deform any shape into any other, and a cycle-consistent loss on pointclouds to regularize the learned deformations.

@inproceedings{groueix19cycleconsistentdeformation,
 title     = {Unsupervised cycle-consistent deformation for shape matching},
 author    = {Groueix, Thibault and Fisher, Matthew and Kim, Vladimir G. and Russell, Bryan and Aubry, Mathieu},
 booktitle = {Symposium on Geometry Processing (SGP)},
 year      = {2019}
}
              

3D-CODED : 3D Correspondences by Deep Deformation ECCV 2018
T. Groueix, , M. Fisher, V. G. Kim , B. C. Russell, M. Aubry
IMAGINE team, Ecole des Ponts ParisTech -- Adobe Research
Paper | Webpage | Slides | Code | Bibtex

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.

@inproceedings{groueix2018b,
 title = {3D-CODED : 3D Correspondences by Deep Deformation},
 author={Groueix, Thibault and Fisher, Matthew and Kim, Vladimir G. and Russell, Bryan and Aubry, Mathieu},
 booktitle = {ECCV},
 year = {2018}
}
              

AtlasNet: A Papier-Mâché Approach to Learning 3D Surface Generation CVPR 2018 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
Paper | Webpage | Adobe Blogpost | Slides | Code | Bibtex

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 strength on an autoencoder, and single-view reconstruction from one still image.

@inproceedings{groueix2018,
  title={{AtlasNet: A Papier-M\^ach\'e Approach to Learning 3D Surface Generation}},
  author={Groueix, Thibault and Fisher, Matthew and Kim, Vladimir G. and Russell, Bryan and Aubry, Mathieu},
  booktitle={Proceedings IEEE Conf. on Computer Vision and Pattern Recognition (CVPR)},
  year={2018}
}
               

Interactive Monte-Carlo Ray-Tracing Upsampling
M. Boughida, T. Groueix , T. Boubekeur
Eurographics Poster, 2016
Abstract | Poster | Slides | Bibtex

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).

@inproceedings {egp.20161048,
  booktitle = {EG 2016 - Posters},
  editor = {Luis Gonzaga Magalhaes and Rafal Mantiuk},
  title = {{Interactive Monte-Carlo Ray-Tracing Upsampling}},
  author = {Boughida, Malik and Groueix, Thibault and Boubekeur, Tamy},
  year = {2016},
  publisher = {The Eurographics Association},
  ISSN = {1017-4656},
  DOI = {10.2312/egp.20161048}
}
           
Talks
teach

Deep 3D deformations
Invited at:

This talk covers my PhD work.



teach

Tutorial: Deep Learning for 3D surface reconstruction
Invited, with Pierre Alain Langlois, at:

thesis

Learning 3D Generation and Matching
T. Groueix
Advisors: Prof. Mathieu Aubry - Prof. Renaud Marlet
IMAGINE team, Ecole des Ponts ParisTech
PDF | Slides | Bibtex | Video | Subject

@inproceedings{groueix2018,
title={{Learning 3D Generation and Matching}},
author={Groueix, Thibault},
school={Ecole Nationale des Ponts et Chaussees},
year={2020}
}
             

teaching
codedemo

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

Star

Atlasnet

Star

Atlasnet V2

Star

3D-CODED

Star

CycleConsistent
Deformation

Star

NetVision

Star

Phd resources

Star

ChamferDistancePytorch


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