Pith. sign in

REVIEW 1 cited by

SCube: Instant Large-Scale Scene Reconstruction using VoxSplats

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2410.20030 v1 pith:TL7BC7IY submitted 2024-10-26 cs.CV cs.AIcs.GR

classification cs.CVcs.AIcs.GR
keywords imagesscubeinputappearancegaussianshigh-resolutionmodelreconstruction
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

We present SCube, a novel method for reconstructing large-scale 3D scenes (geometry, appearance, and semantics) from a sparse set of posed images. Our method encodes reconstructed scenes using a novel representation VoxSplat, which is a set of 3D Gaussians supported on a high-resolution sparse-voxel scaffold. To reconstruct a VoxSplat from images, we employ a hierarchical voxel latent diffusion model conditioned on the input images followed by a feedforward appearance prediction model. The diffusion model generates high-resolution grids progressively in a coarse-to-fine manner, and the appearance network predicts a set of Gaussians within each voxel. From as few as 3 non-overlapping input images, SCube can generate millions of Gaussians with a 1024^3 voxel grid spanning hundreds of meters in 20 seconds. Past works tackling scene reconstruction from images either rely on per-scene optimization and fail to reconstruct the scene away from input views (thus requiring dense view coverage as input) or leverage geometric priors based on low-resolution models, which produce blurry results. In contrast, SCube leverages high-resolution sparse networks and produces sharp outputs from few views. We show the superiority of SCube compared to prior art using the Waymo self-driving dataset on 3D reconstruction and demonstrate its applications, such as LiDAR simulation and text-to-scene generation.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 1 Pith paper

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Sat2City: 3D City Generation from A Single Satellite Image with Cascaded Latent Diffusion

    cs.CV 2025-07 conditional novelty 6.0 of 10

    Sat2City generates explicit 3D city geometry and appearance from a height-map condition using cascaded latent diffusion on sparse voxel grids, beating prior methods on a new synthetic city dataset.

Pith tools