Toward robust analysis of unstructured point-cloud

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 interests focus on the analysis of unstructured data (usually point-clouds) generated by acquiring a physical object or scene, a very hot topic in several research communities (Computer&Graphics, Pattern Recognition, …) and in the industry. Above all the research aspects, I’m considering the following challenges: 1) there is currently no practical formalism allowing to characterize shapes at locals, medium and large scales at once, 2) the notion of a shape scale within an object is still ill-defined, despite a wide range of attempts, 3) very few studies have been published on the transitions between the pertinent scales and shapes of a 3D model.

In addition to these theoretical challenges, I’m also very interested in the applications that could be enhanced by more efficient analysis of raw point clouds: cleaning, reconstruction, abstraction, completion, recognition, etc.

Open positions: group webpage.

NewsTimelineOther activitiesPeopleIndustrial partners


News

  • November 25th 2021: new talk presented at Dagsthul for the Seminar 21471 on Geometric Modeling: Interoperability and New Challenges. Title of the talk: Scale-Space for Machine Learning on 3d Point Clouds. I have also served as Paper Chair for the French conference JFig, supported by the Eurographics French Chapter.
  • October 21th 2021: new paper accepted at Shape Modeling International (SMI’21), introducing Automatic shape adjustment at joints for the Implicit Skinning.
  • September 27th 2021: new paper accepted at ACM ISS 2021, presenting Dynamic Decals: Pervasive Freeform Interfaces Using Constrained Deformable Graphical Elements, in collaboration with Aziz Niyazov and Marcos Serrano. 
  • June 18th 2021: new paper accepted at the Eurographics Symposium on Geometry Processing (SGP) 2021, presenting Stable and efficient differential estimators on oriented point clouds.
  • May 31th 2021: new paper accepted with minor revisions at ACM Transactions on Graphics, introducing PCEDNET : a lightweight neural network for fast and interactive edge detection in 3d point clouds.
  • March 15th 2021: I’ll give a talk entitled Introducing Research in Computer Graphics at Taipey European School/French Section (Japan).
  • January 19th 2021: I gave a talk Introducing Research in Computer Graphics at the High School Louis Feuillade (Montpellier) in the context of La Semaine des Sciences.
  • January 2021: The code of our Eurographics 2020 paper Persistence Analysis of Multi-scale Planar Structure Graph in Point Clouds is now available on GitHub: https://github.com/STORM-IRIT/Plane-Detection-Point-Cloud.
  • previous entries …

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

  • 01/2020-now: Member of the Scientific Committee of the association Les Maths en Scene.
  • 01/2020-06/2020: Scientific consultant at Innersense.
  • 09/2019-12/2019: Scientific consultant at ZEG.ai.

People

Opportunities: checkout https://www.irit.fr/STORM/site/open-positions/.

PhD students:

  • Chems-Eddine Himeur (co-supervised with Loic Barthe and AlphaWind): 3D+time reconstruction of operating wind turbines for remote inspection
  • Francois Gaits (co-supervised with Adrian Basarab): medical imaging and augmented reality
  • Aziz Niyazov (co-supervised with Loic Barthe, Marcos Serrano): interaction for pervasive freeform interfaces

Engineers (Scientific Supervision):

Master students:

Undergrad students:

Alumni:

  • Jie Shao (PhD. Co-advisor: Wuming Zhang): point-cloud registration and processing
  • Thibault Lejemble (PhD. Co-advisor: Loic Barthe): shape analysis
  • 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
  • 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