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

arXiv: https://arxiv.org/abs/2608.17988 · HTML: https://mlsanity.com/paper/2608.17988/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 36 of its 45 references that are in the map.
- First posted on arXiv 18 Aug 2026.

## Builds on (most cited first, 30 of 36)

- [3D Gaussian Splatting for Real-Time Radiance Field Rendering](https://mlsanity.com/paper/2308.04079/) (2023)
- [DreamFusion: Text-to-3D using 2D Diffusion](https://mlsanity.com/paper/2209.14988/) (2022)
- [Zero-1-to-3: Zero-shot One Image to 3D Object](https://mlsanity.com/paper/2303.11328/) (2023)
- [Magic3D: High-Resolution Text-to-3D Content Creation](https://mlsanity.com/paper/2211.10440/) (2022)
- [ProlificDreamer: High-Fidelity and Diverse Text-to-3D Generation with Variational Score Distillation](https://mlsanity.com/paper/2305.16213/) (2023)
- [LRM: Large Reconstruction Model for Single Image to 3D](https://mlsanity.com/paper/2311.04400/) (2023)
- [Structured 3D Latents for Scalable and Versatile 3D Generation](https://mlsanity.com/paper/2412.01506/) (2024)
- [LGM: Large Multi-View Gaussian Model for High-Resolution 3D Content Creation](https://mlsanity.com/paper/2402.05054/) (2024)
- [CLAY: A Controllable Large-scale Generative Model for Creating High-quality 3D Assets](https://mlsanity.com/paper/2406.13897/) (2024)
- [Instant3D: Fast Text-to-3D with Sparse-View Generation and Large Reconstruction Model](https://mlsanity.com/paper/2311.06214/) (2023)
- [GS-LRM: Large Reconstruction Model for 3D Gaussian Splatting](https://mlsanity.com/paper/2404.19702/) (2024)
- [Rodin: A Generative Model for Sculpting 3D Digital Avatars Using Diffusion](https://mlsanity.com/paper/2212.06135/) (2022)
- [Direct3D: Scalable Image-to-3D Generation via 3D Latent Diffusion Transformer](https://mlsanity.com/paper/2405.14832/) (2024)
- [XCube: Large-Scale 3D Generative Modeling using Sparse Voxel Hierarchies](https://mlsanity.com/paper/2312.03806/) (2023)
- [Native and Compact Structured Latents for 3D Generation](https://mlsanity.com/paper/2512.14692/) (2025)
- [MeshLRM: Large Reconstruction Model for High-Quality Meshes](https://mlsanity.com/paper/2404.12385/) (2024)
- [CityDreamer: Compositional Generative Model of Unbounded 3D Cities](https://mlsanity.com/paper/2309.00610/) (2023)
- [3DTopia: Large Text-to-3D Generation Model with Hybrid Diffusion Priors](https://mlsanity.com/paper/2403.02234/) (2024)
- [DiffGS: Functional Gaussian Splatting Diffusion](https://mlsanity.com/paper/2410.19657/) (2024)
- [DiffSplat: Repurposing Image Diffusion Models for Scalable Gaussian Splat Generation](https://mlsanity.com/paper/2501.16764/) (2025)
- [GaussianCube: A Structured and Explicit Radiance Representation for 3D Generative Modeling](https://mlsanity.com/paper/2403.19655/) (2024)
- [Generative Gaussian Splatting for Unbounded 3D City Generation](https://mlsanity.com/paper/2406.06526/) (2024)
- [Baking Gaussian Splatting into Diffusion Denoiser for Fast and Scalable Single-stage Image-to-3D Generation and Reconstruction](https://mlsanity.com/paper/2411.14384/) (2024)
- [SynCity: Training-Free Generation of 3D Worlds](https://mlsanity.com/paper/2503.16420/) (2025)
- [Sat2Density: Faithful Density Learning from Satellite-Ground Image Pairs](https://mlsanity.com/paper/2303.14672/) (2023)
- [Sat2Scene: 3D Urban Scene Generation from Satellite Images with Diffusion](https://mlsanity.com/paper/2401.10786/) (2024)
- [UrbanWorld: An Urban World Model for 3D City Generation](https://mlsanity.com/paper/2407.11965/) (2024)
- [Sat2City: 3D City Generation from A Single Satellite Image with Cascaded Latent Diffusion](https://mlsanity.com/paper/2507.04403/) (2025)
- [A Lesson in Splats: Teacher-Guided Diffusion for 3D Gaussian Splats Generation with 2D Supervision](https://mlsanity.com/paper/2412.00623/) (2024)
- [Seeing through Satellite Images at Street Views](https://mlsanity.com/paper/2505.17001/) (2025)

## Built on by (most cited first, 2 of 2)

- [Revisiting Local Context for Long-Horizon Streaming 3D Reconstruction](https://mlsanity.com/paper/2608.27529/) (2026)
- [OuroReward: Sequential Reward Scheduling for Reinforcement Learning in Text-to-3D Generation](https://mlsanity.com/paper/2610.03423/) (2026)

## Abstract (arXiv)

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.