Artistic Mesh Generation

[kdbp]

This is a pretty interesting paper!

https://github.com/user-attachments/assets/d7868deb-f88e-4a23-a723-d63e53bf695e

[EdgeRunner: Auto-regressive Auto-encoder for Artistic Mesh Generation]

Abstract :

Current auto-regressive mesh generation methods suffer from issues such as incompleteness, insufficient detail, and poor generalization. In this paper, we propose an Auto-regressive Auto-encoder (ArAE) model capable of generating high-quality 3D meshes with up to 4,000 faces at a spatial resolution of 512 [3]. We introduce a novel mesh tokenization algorithm that efficiently compresses triangular meshes into 1D token sequences, significantly enhancing training efficiency. Furthermore, our model compresses variable-length triangular meshes into a fixed-length latent space, enabling training latent diffusion models for better generalization. Extensive experiments demonstrate the superior quality, diversity, and generalization capabilities of our model in both point cloud and image-conditioned mesh generation tasks.

https://research.nvidia.com/labs/dir/edgerunner/ https://www.catalyzex.com/code/3DTopia/OpenLRM