TetraDiffusion: Tetrahedral Diffusion Models for 3D Shape Generation

TL;DR

TetraDiffusion introduces a novel tetrahedral diffusion model for efficient, high-resolution 3D shape generation that outperforms existing methods in speed and quality, enabling near real-time sampling and conditioning on 2D images.

Contribution

It is the first diffusion model operating on tetrahedral partitions for 3D shapes, enabling fast, high-resolution generation with attribute integration.

Findings

Up to 200 times faster inference than existing methods

Supports high-resolution 3D shape generation with attributes

Operates on standard consumer hardware with real-time capabilities

Abstract

Probabilistic denoising diffusion models (DDMs) have set a new standard for 2D image generation. Extending DDMs for 3D content creation is an active field of research. Here, we propose TetraDiffusion, a diffusion model that operates on a tetrahedral partitioning of 3D space to enable efficient, high-resolution 3D shape generation. Our model introduces operators for convolution and transpose convolution that act directly on the tetrahedral partition, and seamlessly includes additional attributes such as color. Remarkably, TetraDiffusion enables rapid sampling of detailed 3D objects in nearly real-time with unprecedented resolution. It's also adaptable for generating 3D shapes conditioned on 2D images. Compared to existing 3D mesh diffusion techniques, our method is up to 200 times faster in inference speed, works on standard consumer hardware, and delivers superior results.