We present Smol-GS, a novel method for learning compact representations for 3D Gaussian Splatting (3DGS). Our approach learns highly efficient splat-wise features to model 3D space which capture abstracted cues, including color, opacity, transformation, and material properties. We propose octree-derived positional encoding, which explicitly models spatial locality and enhances representation efficiency. We further apply entropy-based compression to exploit feature redundancy, and compress splat coordinates using a recursive voxel hierarchy. This design enables orders-of-magnitude storage reduction while preserving representation flexibility. Smol-GS achieves state-of-the-art compression performance on standard benchmarks with high-level rendering quality.
@article{arxiv.2512.00850,
title = {Smol-GS: Compact Representations for Abstract 3D Gaussian Splatting},
author = {Haishan Wang and Mohammad Hassan Vali and Arno Solin},
journal= {arXiv preprint arXiv:2512.00850},
year = {2026}
}