Project description:
Framework to automatically analyze, synthesize and evaluate 3D human motion data. It is today possible to capture time-varying 3D point clouds at high spatial and temporal resolution. This allows in particular for high-quality acquisitions of humans in motion. The main goal of 3DMOVE was to develop tools to process and analyze these data robustly and automatically. Such tools are critical to learning generative models of dynamic human motion, which can in turn 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, where plausible synthesis can aid in creating realism. In addition to automatic tools that allow to synthesize novel 3D human motions based on unprocessed time-varying 3D point clouds from state-of-the-art acquisition systems, 3DMOVE studied frameworks that allow to evaluate the resulting human animations.
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
Financing period: 2019 – 2025
Financing agency: ANR
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
End of project mini-Workshop, December 2 and 3, 2024, at Inria at the Universite Grenoble Alpes:
2.12.2024
14h00-14h30 Stefanie Wuhrer, researcher at Inria Grenoble: Overview of results of the 3DMOVE project
14h30-16h00 : Anne-Hélène Olivier, assistant prof. at Rennes University and Ludovic Hoyet, researcher at Inria Rennes: Populating virtual worlds: Leveraging VR to create the next generation of immersive crowd
3.12.2024
09h00-09h30 Rim Rekik, Ph.D. student at Inria Grenoble: Evaluation of human motion
09h30-10h00 Coffee break
10h00-11h00 Katja Zibrek, researcher at Inria Rennes: The importance of animation in virtual human design
11h00-11h30 Aymen Merrouche, Ph.D. student at Inria Grenoble: 3D motion reconstruction
11h30-12h00 Antoine Dumoulin, Ph.D. student at Inria Grenoble: Data-driven dynamic cloth modeling
