Toward Mesh-Invariant 3D Generative Deep Learning with Geometric Measures

Thomas Besnier, Sylvain Arguillère, Emery Pierson, Mohamed Daoudi

Abstract: Highlights•Registration and generative learning can be performed simultaneously on inconsistent databases of meshes.•Kernel metrics on geometric measures provide efficient loss functions for generative models.•Unsupervised generative models applied on 3D face data provides faster interpolation and expression transfer.