Research

The goal of IMAGINE is to develop a new generation of models, algorithms and interactive environments for easily creating and conveying animated 3D scenes.

Our insight is to revisit models for shapes, motion, stories and virtual cinematography from a user-centred perspective, i.e. to give models an intuitive, predictable behaviour from the user’s view-point. This will ease both semi-automatic generation of animated 3D content and fine tuning of the results.

We are focusing on 4 research axes:

Axis 1. High-level, user-centered models for shapes

Such as

  • Constructive implicit modeling.
  • Creased paper modeling.
  • Free-form sculpture.
  • Homology computation.
  • Spline surface models for arbitrary topologies.
  • Sketch-based modeling and shape editing.

Axis 2. Models for real-time motion synthesis

Such as

  • Frame-based simulation of deformable solids.
  • Geometrical methods for skinning character animations.
  • Volume preserving Free-Form Deformations.

Axis 3. Knowledge-based models for narrative design

Such as

  • Action representation, segmentation and recognition.
  • Computational model of film editing.
  • French translation of the Foundational Model of Anatomy (FMA) ontology.

Axis 4. Creating and interacting with virtual prototypes

Such as

  • Advanced tools for 2D and 3D interaction.
  • Creating arbitrary shapes through combined sketching and sculpting gestures.
  • Interactive systems for motion and narrative content creation.