Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

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

About

We present XCube (abbreviated as $\mathcal{X}^3$), 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. The source code and more results can be found at https://research.nvidia.com/labs/toronto-ai/xcube/.

Xuanchi Ren, Jiahui Huang, Xiaohui Zeng, Ken Museth, Sanja Fidler, Francis Williams• 2023

Related benchmarks

TaskDatasetResultRank
3D Scene GenerationKITTI-360
FID94.822
14
3D Semantic Scene ReconstructionKITTI-360 (test)
IoU99.97
7
Outdoor 3D Scene GenerationWaymo Open Dataset Unconditional
Coverage (CD)27.5
4
Outdoor Scene GenerationWaymo Open Dataset User Study
Rank2
4
Showing 4 of 4 rows

Other info

Follow for update