INRIA Grenoble PhD Seminars

May 2026 (2)

Speakers :

• Antoine Dumoulin, PhD student at MORPHEO team (Inria) : Data-driven Dynamic Garment
  Website Slides
   A lot of applications using digital avatars have been developed in the past few years. Clothing avatars has been a subject of interest for several decades in real-time applications such as video games, and also in offline animations. Nevertheless, modeling physically consistent garment in motion is still a challenging task.
   In this talk, I will present a method to dynamically deform 3D garments, in the form of a 3D polygon mesh, based on body shape, motion, and physical cloth material properties. Existing work studies pose-dependent garment modeling from example data, and possibly data-driven dynamic cloth simulation to generate realistic garments in motion.
   We propose a learning-based approach trained on new data generated with a physics-based simulator. Compared to prior work, our 3D generative model learns garment deformations conditioned by physical material properties, which allows to model loose cloth geometry, especially for large deformations and dynamic wrinkles driven by body motion. Furthermore, the model can be efficiently fitted to observations captured using vision sensors such as 3D point clouds. We leverage the capability of diffusion models to learn flexible and powerful generative priors by modeling the 3D garment in a 2D parameter space independently from the mesh resolution. This representation allows to learn a template-specific latent diffusion model. This allows to condition global and local geometry with body and cloth material information.


• Guillaume Mestdagh, postdoc at TRIPOP team (Inria) : Vertex-based models for simulation of growing plant tissue
  Website Slides Video 1 Video 2
   A plant tissue is composed of cells filled with pressurized water encased in a rigid cell wall structure. Growth occurs when the cell wall yields due inner pressure forces. This high pressure is due to osmosis, a chemical process by which water is attracted into compartments with high solute concentration. Vertex-based models, where cells are represented by polygons connected through their common edges, have successfully captured the mechanical interplay between water and cell walls. However, accounting for osmosis and solute dynamics in these models remains a challenge. In this presentation, I will present a vertex-based model for growing plant tissues where chemical and mechanical effects are coupled using a variational formalism. I will show that the resulting formulation leads to a straightforward numerical implementation, and I will illustrate the model flexibility on a few numerical examples.