The 3D-SAM - Modeling and Analysis of Static and Dynamic Shapes team develops new models and algorithms for analysing and synthesising human movement and behaviour (bodies, faces and gestures). Our approaches are generally derived from computer vision, multimodal artificial intelligence and geometry.

Research themes:

• Modelling, representation and learning of temporal sequences of human body shapes.
• Analysis and synthesis of human movement (body, gestures and face), taking into account interactions between individuals and multimodality.
• Comparison, interpolation and generation of 3D human body shapes.
• Applications: we give priority to work related to the health, sports and creative industry sectors.