cv
General Information
| Full Name | Thomas Besnier |
| thobsn1@gmail.com | |
| Website | https://tbesnier.github.io/ |
Employment History
-
2026 - 2027 Postdoc
Pioneer Centre for AI, University of Copenhagen, DK -
2023 - 2023 Visiting Scholar
Center for Imaging Science (CIS), Johns Hopkins University, US -
2022 - 2025 Ph.D.
CRIStAL, University of Lille, FR -
2022 - 2022 Research Internship
DIKU, University of Copenhagen, DK -
2020 - 2021 Data Scientist Intern
Electro Depot (retail company)
Education
-
2022 - 2025 Ph.D.
University of Lille - Thesis title: Reparametrization invariance in geometric deep learning: applications to human body and face motion synthesis.
-
2018 - 2022 M.Sc. Computer Science Engineering
Centrale Lille Institut - Research internship title: On stochastic shape analysis and applications to phylogenetics.
-
2018 - 2022 M.Sc. Mathematics
University of Lille - Thesis title: On reparameterization invariance and applications to geometric neural networks.
Research Publications
-
Preprint
- F. Nocentini, T. Besnier, C. Ferrari, S. Berretti, and M. Daoudi, "Freetalk: Emotional topology-free 3D talking heads," 2026. arXiv: 2603.15512 [cs.CV]. URL: https://arxiv.org/abs/2603.15512.
-
Journal Articles
- F. Nocentini, T. Besnier, C. Ferrari, S. Arguillere, S. Berretti, and M. Daoudi, "Beyond fixed topologies: Unregistered training and comprehensive evaluation metrics for 3D talking heads," International Journal of Computer Vision, vol. 134, 2026. eprint: 2410.11041 [cs.CV]. URL: https://link.springer.com/article/10.1007/s11263-025-02726-7.
- T. Besnier, S. Arguillere, and M. Daoudi, "Scanmove: Motion prediction and transfer for unregistered body meshes," Computers & Graphics, vol. 132, p. 104409, 2025. DOI: https://doi.org/10.1016/j.cag.2025.104409.
- T. Besnier, E. Pierson, S. Arguillere, and M. Daoudi, "Toward mesh-invariant 3D generative deep learning with geometric measures," Computers & Graphics, 2023. DOI: https://doi.org/10.1016/j.cag.2023.06.027.
-
Conference Proceedings
- T. Besnier, E. Pierson, S. Arguillere, M. Ovsjanikov, and M. Daoudi, "Partial non-rigid deformations and interpolations of human body surfaces," in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2026. arXiv: 2412.02306 [cs.CV]. URL: https://arxiv.org/abs/2412.02306.
- F. Nocentini, T. Besnier, C. Ferrari, S. Arguillere, S. Berretti, and M. Daoudi, "Scantalk: 3D talking heads from unregistered scans," in Proceedings of the European Conference on Computer Vision (ECCV), 2024.
- E. Baker, T. Besnier, and S. Sommer, "A function space perspective on stochastic shape evolution," in Image Analysis, R. Gade, M. Felsberg, and J.-K. Kamarainen, Eds., Cham: Springer Nature Switzerland, 2023, pp. 278-292.
- E. Pierson, T. Besnier, M. Daoudi, and S. Arguillere, "Parameterization Robustness of 3D Auto-Encoders," in Eurographics Workshop on 3D Object Retrieval, S. Berretti, T. Theoharis, M. Daoudi, C. Ferrari, and R. C. Veltkamp, Eds., The Eurographics Association, 2022. DOI: 10.2312/3dor.20221180.
Skills
| Languages | Strong reading, writing and speaking competencies in English and French (mother tongue). |
| Coding | Python, C++, SQL, LaTeX, ... |
| Databases | MySQL, PostgreSQL, SparkSQL |
| Web Dev | HTML, CSS, JavaScript |
| Misc. | Academic research, teaching, LaTeX typesetting and publishing. |
Teaching
-
Time Series Analysis
Teaching Assistant 12h -
Web Development
Teaching Assistant 32h -
Machine Learning
Teaching Assistant 10h -
Databases
Teaching Assistant 12h -
Introduction to Deep Learning
Lead Instructor 20h
Professional Service
-
2023 3DOR2023
Conference Event Organization - Local organizer for the Symposium on 3D Object Retrieval 2023 (3DOR'23).
-
2024 Joint CAP/RFIAP 2024
Conference Event Organization - Local organizer for CAP (Conference sur l'Apprentissage automatique) and RFIAP (Reconnaissance des Formes, Image, Apprentissage et Perception), held on July 1st-3rd 2024.
-
2025 FG 2025
Conference Event Organization - Web Chair for the 19th IEEE International Conference on Automatic Face and Gesture Recognition (FG 2025).
Talks
- Geometry for Statistics and AI (G-StAI) workshop. On robust learning of surface deformations.
Reviewing Experience
- Computers & Graphics
- IEEE Transactions on Circuits and Systems for Video Technology
- Computer Vision and Image Understanding (CVIU)
- IEEE International Conference on Automatic Face and Gesture Recognition (FG)