Project

To achieve this goal, 4D-shape is articulated around 3 objectives:

• 3D-to-3D

 Our first objective concerns the development of a discretization-invariant 3D-to-3D registration and reconstruction framework adapted to human body shapes through a common latent space.

• 3D-to-4D

In the second objective, we plan to investigate the extension of time-static (3D) to time-dynamic (4D) data. The central ingredient in his part of the research will be the construction of a non-linear structure on human shape latent spaces, which will enable us to accurately model the intricate nature of real-life human body motions and deformations. Our approach will use a combination of data-driven methods and physically motivated, elastic deformation energies.

• Prompt-to-3D/4D

In our third and final objective, we aim to learn a mapping from several prompt spaces to the space of human shapes; here the prompt space could be simply a text input space but also a more complicated space such as a voice recording or even an animated human sketch.