Executive Summary
This report details the work completed to achieve deliverable D1.3-Numerical Dataset. The data presented consists of two modalities: first, a dataset of interactions between two people that was captured with MoCap suits at the INRIA facilities; and second, a dataset of dense 3D crowd motions that were synthetically simulated using state-of-the-art crowd simulation software and then lifted to 3D by rigging 3D characters following the trajectories obtained by the simulator. Both datasets contain detailed numerical information, including 3D body pose parameters and global position, as well as images and renders that can be leverage to train data-driven crowd simulation and body interaction algorithms.
