Score: 1

Smol-GS: Compact Representations for Abstract 3D Gaussian Splatting

Published: November 30, 2025 | arXiv ID: 2512.00850v1

By: Haishan Wang, Mohammad Hassan Vali, Arno Solin

Potential Business Impact:

Shrinks 3D scenes to tiny sizes, keeping detail.

Business Areas:
Image Recognition Data and Analytics, Software

We present Smol-GS, a novel method for learning compact representations for 3D Gaussian Splatting (3DGS). Our approach learns highly efficient encodings in 3D space that integrate both spatial and semantic information. The model captures the coordinates of the splats through a recursive voxel hierarchy, while splat-wise features store abstracted cues, including color, opacity, transformation, and material properties. This design allows the model to compress 3D scenes by orders of magnitude without loss of flexibility. Smol-GS achieves state-of-the-art compression on standard benchmarks while maintaining high rendering quality. Beyond visual fidelity, the discrete representations could potentially serve as a foundation for downstream tasks such as navigation, planning, and broader 3D scene understanding.

Country of Origin
🇫🇮 Finland

Page Count
19 pages

Category
Computer Science:
CV and Pattern Recognition