OctFusion: Octree-based Diffusion Models for 3D Shape Generation

dc.contributor.authorXiong, Bojunen_US
dc.contributor.authorWei, Si-Tongen_US
dc.contributor.authorZheng, Xin-Yangen_US
dc.contributor.authorCao, Yan-Peien_US
dc.contributor.authorLian, Zhouhuien_US
dc.contributor.authorWang, Peng-Shuaien_US
dc.contributor.editorAttene, Marcoen_US
dc.contributor.editorSellán, Silviaen_US
dc.date.accessioned2025-06-20T07:40:26Z
dc.date.available2025-06-20T07:40:26Z
dc.date.issued2025
dc.description.abstractDiffusion 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.en_US
dc.description.number5
dc.description.sectionheadersShape Segmentation and Texturing
dc.description.seriesinformationComputer Graphics Forum
dc.description.volume44
dc.identifier.doi10.1111/cgf.70198
dc.identifier.issn1467-8659
dc.identifier.pages13 pages
dc.identifier.urihttps://doi.org/10.1111/cgf.70198
dc.identifier.urihttps://diglib.eg.org/handle/10.1111/cgf70198
dc.publisherThe Eurographics Association and John Wiley & Sons Ltd.en_US
dc.rightsAttribution 4.0 International License
dc.rights.urihttps://creativecommons.org/licenses/by/4.0/
dc.subjectCCS Concepts: Computing methodologies → Shape modeling; Diffusion models; Neural networks
dc.subjectComputing methodologies → Shape modeling
dc.subjectDiffusion models
dc.subjectNeural networks
dc.titleOctFusion: Octree-based Diffusion Models for 3D Shape Generationen_US
Files
Original bundle
Now showing 1 - 2 of 2
Loading...
Thumbnail Image
Name:
cgf70198.pdf
Size:
26.12 MB
Format:
Adobe Portable Document Format
Loading...
Thumbnail Image
Name:
fp2-1011_mm.pdf
Size:
7.52 MB
Format:
Adobe Portable Document Format
Collections