Human4D ANR project takes up new challenges in the context of human body modeling, aiming at a new, efficient 4D shape modelling of human body under motion. Our ambition is to go beyond existing shape space representations that mostly focus on static shape poses, and seldom consider the continuous dynamic of body shapes.

This project aims to develop new representations of human shape in motion that can learn moving shape properties and, as such, can greatly impact 3D and 4D body modeling. These representations should enable the recent learning techniques to be extended from 2D regular grids to dynamic 3D entities.