TetraDiffusion: Tetrahedral Diffusion Models for 3D Shape Generation
This addresses the challenge of slow and resource-intensive 3D content creation for applications like gaming and VR, representing a significant improvement rather than an incremental step.
The paper tackles the problem of extending denoising diffusion models to 3D shape generation by proposing TetraDiffusion, which uses a tetrahedral partitioning for efficient, high-resolution generation, achieving up to 200 times faster inference speed compared to existing methods.
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.