Project description:
It is now possible to capture time-varying 3D point clouds at high spatial and temporal resolution. This allows for high-quality acquisitions of human bodies and faces in motion. However, tools to process and analyze these data robustly and automatically are missing. Such tools are critical to learning generative models of human motion, which can be leveraged to create plausible synthetic human motion sequences. This has the potential to influence virtual reality applications such as virtual change rooms or crowd simulations. Developing such tools is challenging due to the high variability in human shape and motion and due to significant geometric and topological acquisition noise present in state-of-the-art acquisitions. The main objective of 3DMOVE is to automatically compute high-quality generative models from a database of raw dense 3D motion sequences for human bodies and faces. To achieve this objective, 3DMOVE will leverage recently developed deep learning techniques.
Members:
Scientific leader:
- Stefanie Wuhrer, Inria
Permanent members:
- Anne-Hélène Olivier, Université Rennes 2
- Jean-Sébastien Franco, Grenoble INP
- Edmond Boyer, Inria, until Nov. 2022
Ph.D. students:
- Rim Rekik Dit Nkhili (Ph.D. student at Université Grenoble Alpes since Nov. 2021)
Co-advised by Anne-Hélène Olivier and Stefanie Wuhrer - Mathieu Marsot (Ph.D. student at Université Grenoble Alpes Nov. 2019 – May 2023)
Title of thesis: Data driven representation and synthesis of 3D human motion
Date of thesis defense: May 2023
Co-advised by Jean-Sébastien Franco and Stefanie Wuhrer - Raphaël Dang-Nhu (Ph.D. student at Université Grenoble Alpes Oct. 2020 – Apr. 2021)
Co-advised by Anne-Hélène Olivier and Stefanie Wuhrer
Publications:
- Rim Rekik, Stefanie Wuhrer, Ludovic Hoyet, Katja Zibrek, Anne-Hélène Olivier. A Survey on Realistic Virtual Human Animations: Definitions, Features and Evaluations. Computer Graphics Forum, 2024.
- Rim Rekik*, Mathieu Marsot*, Anne-Hélène Olivier, Jean-Sébastien Franco, Stefanie Wuhrer. Correspondence-free online human motion retargeting. International Conference on 3D Vision, 2024.
* authors with equal contribution
Code is available at https://gitlab.inria.fr/rrekikdi/human-motion-retargeting2023 - Matthieu Armando , Laurence Boissieux, Edmond Boyer, Jean-Sébastien Franco, Martin Humenberger, Christophe Legras, Vincent Leroy, Mathieu Marsot, Julien Pansiot, Sergi Pujades, Rim Rekik Dit Nekhili, Grégory Rogez, Anilkumar Swamy, Stefanie Wuhrer.
4DHumanOutfit: a multi-subject 4D dataset of human motion sequences in varying outfits exhibiting large displacements. Computer Vision and Image Understanding, 2023.
Dataset is available at https://kinovis.inria.fr/4dhumanoutfit/
- Mathieu Marsot, Stefanie Wuhrer, Jean-Sébastien Franco, Anne Hélène Olivier. Representing motion as a sequence of latent primitives, a flexible approach for human motion modelling. Research report 2022.
Code is available at https://gitlab.inria.fr/mmarsot/new_segmentation - Mathieu Marsot, Stefanie Wuhrer, Jean-Sébastien Franco, Stephane Durocher. A Structured Latent Space for Human Body Motion Generation. International Conference on 3D Vision, 2022.
Code is available at https://github.com/mmarsot/A_structured_latent_space
Financing period: 2019 – 2025
Financing agency: ANR