OctFusion: Octree-based Diffusion Models for 3D Shape Generation
This work addresses the problem of slow and inefficient 3D shape generation for applications in computer graphics and AI, representing an incremental improvement over existing diffusion-based methods.
The paper tackles the challenge of efficiently generating diverse and high-quality 3D shapes with diffusion models by introducing OctFusion, which achieves state-of-the-art performance on ShapeNet and Objaverse datasets, generating shapes in 2.5 seconds on a single GPU with guaranteed continuous and manifold meshes.
Diffusion models have emerged as a popular method for 3D generation. However, it is still challenging for diffusion models to efficiently generate diverse and high-quality 3D shapes. In this paper, we introduce OctFusion, which can generate 3D shapes with arbitrary resolutions in 2.5 seconds on a single Nvidia 4090 GPU, and the extracted meshes are guaranteed to be continuous and manifold. The key components of OctFusion are the octree-based latent representation and the accompanying diffusion models. The representation combines the benefits of both implicit neural representations and explicit spatial octrees and is learned with an octree-based variational autoencoder. The proposed diffusion model is a unified multi-scale U-Net that enables weights and computation sharing across different octree levels and avoids the complexity of widely used cascaded diffusion schemes. We verify the effectiveness of OctFusion on the ShapeNet and Objaverse datasets and achieve state-of-the-art performances on shape generation tasks. We demonstrate that OctFusion is extendable and flexible by generating high-quality color fields for textured mesh generation and high-quality 3D shapes conditioned on text prompts, sketches, or category labels. Our code and pre-trained models are available at https://github.com/octree-nn/octfusion.