Problem
Research questions and friction points this paper is trying to address.
3D Gaussian Splatting
structured latent
large-scale 3D generation
aerial scene
GS-Voxel: Fitting-Free Structured Latents for Large-Scale 3DGS Generation
🤖 AI Summary
该研究解决了3DGS重建的无序和不规则问题，通过GS-Voxel框架将其转换为结构化的稀疏体素，并使用VAE编码几何和属性，实现大规模3D场景生成。
📝 Abstract
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.
Innovation
Methods, ideas, or system contributions that make the work stand out.
Fitting-Free Structured Latents
3D Gaussian Splatting (3DGS)
Sparse Active Voxels
Factorized VAE
Image-Conditioned Flow Models
🔎 Similar Papers
No similar papers found.
