NeuralGS：融合神經場與3D高斯潑濺技術，實現緊湊的3D表徵

NeuralGS: Bridging Neural Fields and 3D Gaussian Splatting for Compact 3D Representations

March 29, 2025

作者: Zhenyu Tang, Chaoran Feng, Xinhua Cheng, Wangbo Yu, Junwu Zhang, Yuan Liu, Xiaoxiao Long, Wenping Wang, Li Yuan

cs.AI

摘要

3D高斯泼溅（3DGS）展现了卓越的质量与渲染速度，但伴随着数百万个3D高斯分布以及显著的存储与传输成本。近期的3DGS压缩方法主要聚焦于压缩Scaffold-GS，虽取得了令人瞩目的性能，却引入了额外的体素结构及复杂的编码与量化策略。本文旨在开发一种名为NeuralGS的简洁而高效的方法，探索另一种途径将原始3DGS压缩为紧凑表示，无需体素结构及复杂量化策略。我们观察到，如NeRF等神经场能够利用多层感知机（MLP）神经网络仅以数兆字节表示复杂的3D场景。因此，NeuralGS有效采用神经场表示，通过MLPs编码3D高斯的属性，即便对于大规模场景也仅需极小存储空间。为实现这一目标，我们采用聚类策略，并根据高斯的重要性评分作为拟合权重，为每个聚类拟合不同的微型MLPs。我们在多个数据集上进行实验，实现了平均45倍的模型大小缩减，且未损害视觉质量。我们的方法在原始3DGS上的压缩性能与专门基于Scaffold-GS的压缩方法相当，这展示了直接利用神经场压缩原始3DGS的巨大潜力。

English

3D Gaussian Splatting (3DGS) demonstrates superior quality and rendering speed, but with millions of 3D Gaussians and significant storage and transmission costs. Recent 3DGS compression methods mainly concentrate on compressing Scaffold-GS, achieving impressive performance but with an additional voxel structure and a complex encoding and quantization strategy. In this paper, we aim to develop a simple yet effective method called NeuralGS that explores in another way to compress the original 3DGS into a compact representation without the voxel structure and complex quantization strategies. Our observation is that neural fields like NeRF can represent complex 3D scenes with Multi-Layer Perceptron (MLP) neural networks using only a few megabytes. Thus, NeuralGS effectively adopts the neural field representation to encode the attributes of 3D Gaussians with MLPs, only requiring a small storage size even for a large-scale scene. To achieve this, we adopt a clustering strategy and fit the Gaussians with different tiny MLPs for each cluster, based on importance scores of Gaussians as fitting weights. We experiment on multiple datasets, achieving a 45-times average model size reduction without harming the visual quality. The compression performance of our method on original 3DGS is comparable to the dedicated Scaffold-GS-based compression methods, which demonstrate the huge potential of directly compressing original 3DGS with neural fields.