I am a CNRS researcher, working at the STORM research group, in the IRIT laboratory, Toulouse.
I am also an associate researcher of Archeovision, a CNRS laboratory studying how Cultural Heritage researches can be leveraged by the acquisition, modeling and processing of 3D data. My research activities follow 3 main directions.

Unstructured Data Analysis

My main research interest is to focus on the analysis of unstructured data (e.g. 3d point clouds). Such data are usually acquired from a physical object or scene, which are often very complex and large. The resulting point clouds can be made of billions of samples, perturbed by noise, holes and other defects.

The goal of my research is to develop models and technics to analyze and process such unstructured data. In other words, we want to classify, recognize, reconstruct, and simplify billions of samples using practicable and robust algorithms, extending the state of the art in Computer Graphics, Computer Vision, Artificial Intelligence, and related topics.

My research activities on these topics are structured in two different groups:

  • The SSLAM project, which focuses on studying how to leverage the Scale-Space for Machine Learning on 3d Point Clouds. Checkout the group, our results and open positions at https://www.irit.fr/sslam/.
  • The UNREAL research team, which focuses on Unstructured Data Analysis from a more general perspective, and which gather researchers from Mathematics, Robotics and Computer Sciences. Checkout the group, our results and open positions at https://www.irit.fr/unreal/.

Monte Carlo Geometry Processing

Monte Carlo methods provide a practical way to solve many numerical problems in science and engineering. In the field of Computer Graphics, it is used for decades to simulate the transport of light in 3d scenes, and compute (render) physically plausible images. More recently, several work have shown that it can also be used in other context such as Geometry Processing.

My research activities on this topic are split in two orthogonal directions:

  1. Leveraging the design and computational expertise gathered by the Computer Graphics Rendering community in order to efficiently solve the radiative transport equation in Physics.
  2. Exploiting the computational power and scalability of Monte Carlo integration to solve Geometry Processing problems, including (of course) point cloud processing.

Computer Graphics for empowering Augmented Reality in Medical use cases

In this line of work, I collaborate with surgeons and researchers in Medical Imaging, to develop practical Augmented Reality systems in order to improve surgeries. These systems are designed by combining efficient real-time geometry processing and rendering algorithms, and clinical-grade acquisition systems (e.g. ultrasound imager).


Affiliations:

  • CNRS, IRIT, Université de Toulouse, INPT, UPS, UT1C, UT2J, France.
  • CNRS, Archeovision, Université de Bordeaux, France.

Timeline

  • 2016-Now: CNRS researcher (chargé de recherche) at IRIT (Toulouse, France), at the STORM research group.
  • 2014-2016: Post-doc at IRIT, Université Paul-Sabatier (Toulouse, France), with David Vanderhaeghe,
  • 2013-2014: Post-doc at University College London working with Niloy Mitra,
  • 2012-2013: Post-doc at Inria Bordeaux Sud-Ouest (France), working with Pascal Barla, Gaël Guennebaud and ArcheoVision,
  • 2009-2012: PhD thesis at Inria Bordeaux Sud-Ouest (France), supervised by Patrick Reuter and Christophe Schlick.

Other activities


People

Postdoctoral researchers:

  • Mégane Bati, in collaboration with Mathias Paulin.
  • Jules Vidal, in collaboration with Loïc Barthe.

PhD students (Supervision):

  • Chems-Eddine Himeur, co-supervised with Loic Barthe and AlphaWind
  • Francois Gaits, co-supervised with Adrian Basarab
  • Aziz Niyazov, co-supervised with Loic Barthe, Marcos Serrano
  • Pierre Cuquel, co-supervised with Loic Barthe and Dominique Longin

PhD students (Collaboration):

Engineers (Supervision):

  • Gauthier Bouyjou, co-supervised with Adrian Basarab

Master students:

Undergrad students:

Alumni:

  • Matthieu Gomiero (co-supervised with Loic Barthe)
  • Sébastien Egner (Inter. Co-advisor Loic Barthe): point-based shape analysis
  • Nguyen An Thuyen Duong (Intern. Co-advisor Adrian Basarab): image processing
  • Aniket Agarwalla (Google Summer of Code): point-based shape analysis
  • Wilhem Barbier (Inter. Co-advisor Mathias Paulin): computational physics
  • Loic Robert (Inter. Co-advisor Loic Barthe): geometric modeling
  • Jie Shao (PhD. Co-advisor: Wuming Zhang): point-cloud registration and processing
  • Thibault Lejemble (PhD. Co-advisor: Loic Barthe): point-based shape analysis
  • Yann-Situ Gazull (Intern. Co-advisor David Vanderhaeghe): Structural Color Processing
  • Quentin Marcadet (Intern. Co-advisor Loic Espinasse): 3d acquisition
  • Felix Herrmann (Google Summer of Code. Co-advisor Simon Giraudot): point-cloud registration
  • Clément Rodrigues Viguier (Research Engineer. Co-supervisor: David Vanderhaeghe) [Méso-Star]: Structural Color Processing
  • Anahid Ghazanfarpour (PhD. Co-advisor: Jean-Pierre Jessel): mesh processing
  • Filippo Fanni (Intern. Co-advisor: David Vanderhaeghe): Structural Color Processing
  • Necip Fazil Yildiran (Google Summer of Code. Co-advisor Simon Giraudot): point-cloud registration
  • Sandra Alfaro Romero (Intern): point-cloud registration
  • Paul Bernardi (Intern. Co-advisor: David Vanderhaeghe): Structural Color Processing
  • Céline Michaud (PhD. Co-advisor: Mathias Paulin. Company: Oktal-SE): mesh processing
  • Baptiste Delos (Intern. Co-advisor: David Vanderhaeghe): Structural Color Processing
  • Fatemi Arezou (Intern. Co-advisor: David Vanderhaeghe): real-time rendering
  • Xavier Chalut (Intern. Co-advisor: Jean-Pierre Jessel): mesh processing
  • Georges Nader (PhD. Co-advisor: Gaël Guennebaud): shape analysis
  • Bastien Perpère (Engineer. Co-advisors: Gaël Guennebaud, Pascal Barla. Company: The Foundry): rendering

Industrial partners