From September 2022, the GeoViC team has now evolved into two new specialized teams:
Please note that this website does not receive anymore updates, for up-to-date information please check with the respective teams.
Geometric & Visual Computing (GeoViC) is a Computer Graphics and Computer Vision group tackling geometric analysis, modeling and computer animation research.
The team is part of the "Modeling, Simulation & Learning" pole of the LIX (Laboratoire d'Informatique de l'Ecole Polytechnique) in Palaiseau.
It depends of the CNRS and Ecole Polytechnique, IP Paris.
Our approach favors the introduction of efficient structures for high-level, possibly abstract, geometrical features of the studied shapes or phenomena. These structures can either be extracted from existing data or synthesized from prior knowledge and mathematical modeling.
Examples of such structures span latent space obtained from geometric-aware convolutional neural networks, distributions of shape arrangements and their associated metric, intrinsic properties on manifolds such as local-symmetry or Gaussian curvature, non-manifold skeletal structures representing volumetric implicit shapes, visual surface features associated with details or wrinkles on a parent shape, multi-resolution representations of complex shapes, as well as space-time features expressing user-guided or simulated interactions such as contacts and shape deformations.
These structures offer an efficient computational representation highlighting meaningful properties of the digital model and can be used to improve geometry processing algorithms, to provide support for expressive modeling or visualization methods, or to enable efficient and controllable animation.
The results of our research lead to fast and robust virtual content analysis and creation methods such as shape matching and feature retrieval, creative prototyping and modeling of detailed objects or characters that automatically adapt to the context and the user interactions, or either animated natural scenes composed of multiple layers coupling geometrical constraints with efficient simulation. The targeted applications include entertainment & artistic creation (animation cinema, video games, VFX), virtual prototyping & manufacturing, as well as modeling & visualization for natural sciences.
Marie-Julie Rakotosaona has been awared at the second place for the IDIA (Informatics, Data and IA) best thesis prize from Institut Polytechnique de Paris.
Marie-Julie Rakotosaona won the Best Thesis Award from the GDR-IGRV (Groupe de Recherche en Informatique Graphique et Réalité Virtuelle du CNRS).
Vicky Kalogeiton will be part of a collaborative funded project APATE on automatic recognition of DeepFakes.
Vicky Kalogeiton receive a funding for her ANR Jeune Chercheur (ANR JCJC) project “WhyBehindScenes”.
Marie-Paule Cani received the Tosiyasu Kunii Award by the Shape Modeling International committee.
We are welcoming James Gain (Cape Town University) as Invited Researcher in our team for three months.
Congratulation to Marie-Paule Cani who received the Distinguished Career Award from the Eurographics Association.
Welcome to Maysam Behmanesh starting his PostDoc with Maks Ovsjanikov on Geometric Machine Learning.
The paper PointCleanNet (first authored by Marie-Julie Rakotosaona) was the top cited article in the Computer Graphics Forum 2020-2021.
We are happy to welcome Pierre Poulin (Université de Montreal) as Invited Researcher in our team for three months.
Congratulation to Marie-Julie Rakotosaona who succesfully defended her PhD entitled Learning-based representations and methods for 3D shape analysis, manipulation and reconstruction on Dec. the 10th.
Congratulation to Souhaib Attaiki, Gautam Pai, Maks Ovsjanikov for their best paper award at 3DV2021 on “Deep Partial Functional Maps”.
David-Henri Garnier received the Best Paper award at JFIG (Journées Francaises d’Informatique Graphique) for his work on “Growing Optimized Anistoropic Microstructure with Reaction/Diffusion”.
Robin Courant, Christophe Lino, Marc Christie (University of Rennes), and Vicky Kalogeiton received the Best Paper Award at CVEU (ICCV workshop) for their work on “High-Level Features for Movie Style Understanding”. Congratulations to them!
Welcome to our new members: Yasser Benigmim (PhD), Nicolas Dufour (PhD), Ramana Sundararaman (PhD), and Jiong Chen (Post Doc)
Marie-Julie Rakotosaona was interviewed in the CVPR Daily magazine for her work on “Learning Delaunay Surface Elements for Mesh Reconstruction”.
Congratulation to Adrien Poulenard who received one of the “best PhD Award” from IDIA department at IP Paris. Adrien did his PhD with Maks Ovsjanikov on Structures for deep learning and topology optimization of functions on 3D shapes.
We had the pleasure to receive Eric Chahi, video game developer, to share some of our project and ideas with him.
We are glad to receive one of the Honorable Mention of the Best Paper Awards at Eurographics for the work on Velocity Skinning for Real-time Stylized Skeletal Animation.
Videos and codes are available at velocityskinning.com.
Note that this paper has also received the replicability stamp.
The discussion on AI and cooperation that took place during the Science and video games conference in which Vicky Kalogeiton participated (with Antoine bauza and Pierre Beri) is highlighted by Polytechnique. The video of the discussion is available online.
We will be co-organizing the Digital Geometry & Discrete Variational Calculus from March the 29th to April 2nd.
We will be involved in the Colloque Science & Jeux Vidéos that will take place from March 29th to April 1st.
We organised the French working days on Geometry Modeling (GTMG) that took place on the 18th and 19th of March. Thanks to all the participants !
https://gtmg2021.sciencesconf.org
Our work on Affective Language for Visual Art (ArtEmis) using AI to make emotional sense of abstract artwork, developed in collaboration with researchers from Stanford and KAUST, is highlighted in media. [Medium.com], [Polytechnique].
We are happy to welcome Mathieu Desbrun, currently on leave from Caltech, and joining the lab as an Inria senior researcher. We are eager to work with him in the near future, as well as working toward a reshaping of our team.
Congratulation to Mathieu Desbrun who is nominated as ACM fellow.
Congratulation to Thomas Buffet who succesfully defended his PhD (2021/01/13) on the Topic: “Field-based approaches for the collision-free animation of layered and dynamic clothing”.
Congratulation to Pierre Ecormier-Nocca who succesfully defended his PhD (2020/12/03) on the Topic: “Authoring consistent, animated ecosystems: Efficient learning from partial data”.
Congratulation to Renaud Chabrier who succesfully defended his PhD (2020/11/27) on the Topic: “La géométrie de la vie: quand le dessin rencontre les sciences du vivant”.
We are happy to welcome Vicky Kalogeiton who is joining our group as new Assistant Professor at Ecole Polytechnique after conducting her Post doc at VGG, Oxford, and her PhD from Univ. Edinburgh and Inria Grenoble. Vicky brings new expertise in deep learning applied to spatial and temporal localization of objects and phenomenon in videos.
Jiayi Wei will start her PhD in our group at fall on “New Geometric representations for Volumetric Brain Analysis”.
We are glad to welcome two new international PhD students working on the Innovative Training Network CLIPE aiming at “creating lively interactive populated environments” who will join us in fall: Eduardo Alvarado and Ariel Kwiatkowski.
Adrien Poulenard succesfully defended his PhD entitled “Structures for Deep Learning and Topology Optimization for Functions on 3D Shapes”.
Marie-Paule Cani become the President of the Computer Science Department (DIX - Departement d’Informatique de l’Ecole Polytechnique).
Thibault Lescoat succesfully defended his PhD entitled “Geometric operators for 3D modeling using dictionary-based shape representations”.
Marie-Paule Cani is elected as the President of the SIF (Société Informatique de France) scientific steering committee.
Welcome to our 3 new postdocs: Chrisotphe Lino, Gautam Pai, and Liu Zhisong.
We got nominated for the Best Paper at ICCV 2019 for the article Unsupervised Deep Learning for Structured Shape Matching Jean-Michel Roufosse, Abhishek Sharma, Maks Ovsjanikov. There was 7 papers nominated out of 1075 accepted papers, and 4303 submissions.
We received the Best Presentation Award at MIG 2019 for the article Animation Synthesis Triggered by Vocal Mimics, Adrien Nivaggioli, Damien Rohmer.
Marie-Paule Cani was programm co-chair of “Motion, Interaction and Games” (MIG’2019) with Tiberiu Popa.
- Damien Rohmer is program co-chair of the ACM SIGGRAPH / EUROGRAPHICS Symposium on Computer Animation - SCA - 2018, with Maud Marchal (IRISA INSA). SCA took place on 11-13th of July in Paris.
- Pooran Memari and Maks Ovsjanikov, are program co-chair of the EUROGRAPHICS Symposium on Geometry Processing - SGP - 2018, with Tamy Boubekeur (Télécom ParisTech, LTCI). SGP took place on 9-11th of July in Paris.