GROWD: Generative Modelling of Dense Crowds under Multiscale Observations
- Programme
- Bienvenüe+ MSCA-COFUND Fellowship
- Funder
- Région Bretagne (Brittany Regional Council)
- Host
- VirtUs team, Inria Rennes
- Role
- Project Lead / Research Fellow
- Period
- Nov 2026 – Oct 2028 (24 months)
- Total funding
- €131,760
Overview
GROWD is my Bienvenüe+ MSCA-COFUND Fellowship project, an independent research programme that I proposed and developed, hosted by the VirtUs team at Inria Rennes. The project develops probabilistic generative models for dense crowd dynamics by combining sparse, local, fine-grained agent-level observations with dense, global, coarse-grained video-derived measurements.
The project addresses a key limitation in current crowd modelling: existing approaches often either assume unrealistic access to complete individual trajectories or rely on coarse field-level observations that obscure local interactions. GROWD treats these two sources of information as complementary views of the same underlying crowd dynamics.
Research Direction
- Dense crowd modelling: probabilistic, data-informed models of dense crowd dynamics.
- Multiscale observations: integrating agent-level observations with video-derived measurements for uncertainty-aware crowd analysis.
- Generative models: extending my previous work on multi-character interaction synthesis and generative human motion toward crowd-level behaviour.
Collaboration
I am especially interested in collaborations that connect fine-grained human motion, coarse-grained video observations, probabilistic generative modelling, and domain expertise from event organisation or urban planning for safer and more interpretable analysis of shared public spaces.
Funding
Bienvenüe+ is an international postdoctoral fellowship programme co-funded by the European Union’s Horizon Europe Marie Skłodowska-Curie Actions COFUND programme, Région Bretagne, and participating host institutions.