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. More results and details can be found at https://research.nvidia.com/labs/toronto-ai/xcube/.

翻译：我们提出了 $\mathcal{X}^3$（读作 XCube），一种新颖的生成模型，用于具有任意属性的高分辨率稀疏三维体素网格。该模型能够以前馈方式生成高达 $1024^3$ 有效精度的百万级体素，无需耗时的测试时优化。为实现这一目标，我们采用了一种分层体素潜在扩散模型，通过基于高效 VDB 数据结构构建的定制框架，以由粗到细的方式逐步生成更高分辨率的网格。除了生成高分辨率物体外，我们还展示了 XCube 在大型户外场景中的有效性，其尺度可达 100米×100米，体素尺寸小至 10厘米。我们观察到相较于以往方法，在定性和定量结果上均有显著提升。除无条件生成外，该模型还可用于解决多种任务，包括用户引导编辑、单次扫描场景补全以及文本到三维的生成。更多结果与细节请访问 https://research.nvidia.com/labs/toronto-ai/xcube/。