MeshGPT creates triangle meshes by autoregressively sampling from a transformer model that has been trained to produce tokens from a learned geometric vocabulary. These tokens can then be decoded into the faces of a triangle mesh. Our method generates clean, coherent, and compact meshes, characterized by sharp edges and high fidelity.

GitHub Pages

Surface features from an input 3D mesh are encoded through a face convolution-based encoder and decoded through a StyleGAN2-inspired decoder to generate textures directly on the surface of the mesh.

The optimized volumetric representation is shown as a mesh in the middle along with the viewpoint. Novel view panoptics obtained by our method are shown on the right.

Given a 3D mesh of an object, and latent texture code, our genera-tor produces textures directly on the mesh surface. To this end, we parameterize the mesh with a hierarchy of 4-way rotationally symmetric (4-RoSy) fields from QuadriFlow [23] of diferent resolutions.