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

  • April 22th 2022: new oral presentation accepted at the International Radiation Symposium (IRS2022) on Sampling molecular state transitions in a line-by-line Monte Carlo approach to estimate radiative forcing for climate change studies, to be presented by Yaniss Nyffenegger-Pere (Laplace).
  • March 20th 2022: new paper accepted at Eurographics 2022 on Recursive analytic spherical harmonics gradient for spherical lights.
  • March 10th 2022: I’ll give a talk at the Pierre Mendès France high school, talking on 3d geometry and research, in the context of Regards de Geomètre.
  • March 7th 2022: new oral presentation accepted at the International Radiation Symposium 2022. Title: Sampling molecular state transitions in a line-by-line Monte Carlo approach to estimate radiative forcing for climate change studies.
  • January 28th and February 11th: I am serving in the jury of the Eloquensciences contest, organized by the association Les Maths en Scene. I have also advised several students to prepare their talk.
  • February 7th 2022: new invited talk on Scale-Space for Machine Learning on 3d Point Clouds, as part of a lecture cycle in Clermont Ferrand https://master3dia.iut-clermont.fr.
  • Update: January 2022 (May 31th 2021): new paper accepted at ACM Transactions on Graphics, introducing PCEDNET : a lightweight neural network for fast and interactive edge detection in 3d point clouds. Project page: https://storm-irit.github.io/pcednet-supp/.
  • 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.
  • 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/.

Main collaborators: Loic Barthe, David Vanderhaeghe, Mathias Paulin, Adrian Basarab

Postdoctoral researchers:

  • Mégane Bati, in collaboration with Mathias Paulin.

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

PhD students (Collaboration):

Engineers (Supervision):

  • Pierre Cuquel, co-supervised with Loic Barthe and Dominique Longin
  • Gauthier Bouyjou, co-supervised with Adrian Basarab

Master students:

  • Matthieu Gomiero (co-supervised with Loic Barthe)
  • Mohammad El Sakka, Matheo Vidal. Dany Morales (co-supervised with Loic Barthe and Georges Da Costa)

Undergrad students:

Alumni:

  • 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