Skip to yearly menu bar Skip to main content


XCube: Large-Scale 3D Generative Modeling using Sparse Voxel Hierarchies

Xuanchi Ren · Jiahui Huang · Xiaohui Zeng · Ken Museth · Sanja Fidler · Francis Williams

Arch 4A-E Poster #390
award Highlight
[ ]
Wed 19 Jun 10:30 a.m. PDT — noon PDT

Abstract: We present $\mathcal{X}^3$ (pronounced XCube), a novel generative model for high-resolution sparse 3D voxel grids with arbitrary attributes. Our model can generate millions of voxels with a finest effective resolution of up to $1024^3$ in a feed-forward fashion without time-consuming test-time optimization. To achieve this, we employ a hierarchical voxel latent diffusion model which generates progressively higher resolution grids in a coarse-to-fine manner using a custom framework built on the highly efficient VDB data structure. Apart from generating high-resolution objects, we demonstrate the effectiveness of XCube on large outdoor scenes at scales of 100m$\times$100m with a voxel size as small as 10cm. We observe clear qualitative and quantitative improvements over past approaches. In addition to unconditional generation, we show that our model can be used to solve a variety of tasks such as user-guided editing, scene completion from a single scan, and text-to-3D.

Live content is unavailable. Log in and register to view live content