GS-Voxel: Fitting-Free Structured Latents for Large-Scale 3DGS Generation

Hugging Face Daily Papers Papers

Summary

GS-Voxel introduces a fitting-free framework to convert 3D Gaussian Splatting reconstructions into structured latents, enabling scalable generation of large-scale aerial 3D scenes via flow models and tiled inference.

Many scalable latent 3D generators operate on structured tensors, whereas pre-optimized 3D Gaussian Splatting (3DGS) reconstructions are unordered, spatially irregular, and vary widely in primitive count. We present GS-Voxel, a fitting-free structured latent framework, and evaluate it for large-scale aerial 3D Gaussian scene generation. GS-Voxel deterministically converts a compatible pre-optimized 3DGS reconstruction into sparse active voxels without additional per-scene optimization, retaining the sub-voxel positions and rendering attributes of the selected primitives. A GS-specific factorized VAE then separately encodes voxel geometry and local Gaussian attributes into sparse 3D latents whose size grows with the number of occupied voxels rather than being limited by a fixed scene-wide primitive count. We train image-conditioned flow models in the GS-Voxel latent space to generate aerial 3DGS scenes. A key application enabled by GS-Voxel is large-area scene generation: overlap-aware tiled inference extends synthesis beyond a single training crop conditioned on satellite-view images. Our results show that GS-Voxel provides structured latents for pre-optimized aerial 3DGS reconstructions, with latent capacity that grows with the number of occupied voxels.
Original Article
View Cached Full Text

Cached at: 08/19/26, 03:57 AM

Paper page - GS-Voxel: Fitting-Free Structured Latents for Large-Scale 3DGS Generation

Source: https://huggingface.co/papers/2608.17988

Abstract

GS-Voxel converts unstructured 3D Gaussian reconstructions into sparse structured latents to enable scalable aerial scene generation via flow models.

Many scalable latent 3D generators operate on structured tensors, whereas pre-optimized3D Gaussian Splatting(3DGS) reconstructions are unordered, spatially irregular, and vary widely in primitive count. We presentGS-Voxel, a fitting-free structured latent framework, and evaluate it for large-scale aerial 3D Gaussian scene generation.GS-Voxeldeterministically converts a compatible pre-optimized3DGSreconstruction intosparse active voxelswithout additional per-scene optimization, retaining the sub-voxel positions and rendering attributes of the selected primitives. A GS-specificfactorized VAEthen separately encodes voxel geometry and local Gaussian attributes intosparse 3D latentswhose size grows with the number of occupied voxels rather than being limited by a fixed scene-wide primitive count. We train image-conditionedflow modelsin theGS-Voxellatent space to generate aerial3DGSscenes. A key application enabled byGS-Voxelis large-area scene generation: overlap-awaretiled inferenceextends synthesis beyond a single training crop conditioned on satellite-view images. Our results show thatGS-Voxelprovides structured latents for pre-optimized aerial3DGSreconstructions, with latent capacity that grows with the number of occupied voxels.

View arXiv pageView PDFAdd to collection

Get this paper in your agent:

hf papers read 2608\.17988

Don’t have the latest CLI?curl \-LsSf https://hf\.co/cli/install\.sh \| bash

Models citing this paper0

No model linking this paper

Cite arxiv.org/abs/2608.17988 in a model README.md to link it from this page.

Datasets citing this paper0

No dataset linking this paper

Cite arxiv.org/abs/2608.17988 in a dataset README.md to link it from this page.

Spaces citing this paper0

No Space linking this paper

Cite arxiv.org/abs/2608.17988 in a Space README.md to link it from this page.

Collections including this paper0

No Collection including this paper

Add this paper to acollectionto link it from this page.

Similar Articles

Native and Compact Structured Latents for 3D Generation

Papers with Code Trending

This paper introduces O-Voxel, a new sparse voxel representation for 3D generative modeling that efficiently handles complex topologies and appearance, and trains large-scale flow-matching models with 4B parameters to achieve state-of-the-art generation quality.

GlobalSplat: Efficient Feed-Forward 3D Gaussian Splatting via Global Scene Tokens

Hugging Face Daily Papers

GlobalSplat introduces an efficient feed-forward framework for 3D Gaussian splatting that achieves compact and consistent scene reconstruction using global scene tokens, reducing computational overhead and inference time to under 78ms. The method uses a coarse-to-fine training approach to prevent representation bloat while maintaining competitive novel-view synthesis performance with significantly fewer Gaussians (16K) compared to dense baselines.