GaussianForest: Hierarchical-Hybrid 3D Gaussian Splatting for Compressed Scene Modeling

TL;DR

GaussianForest introduces a hierarchical hybrid 3D Gaussian approach for scene modeling that significantly compresses data while maintaining high rendering quality and speed, advancing novel-view synthesis efficiency.

Contribution

It proposes a novel hierarchical Gaussian forest framework with adaptive growth and pruning, enabling over 10x compression in 3D scene representation.

Findings

Achieves over 10x data compression compared to existing methods.

Maintains comparable rendering quality and speed.

Effectively models complex scenes with fewer parameters.

Abstract

The field of novel-view synthesis has recently witnessed the emergence of 3D Gaussian Splatting, which represents scenes in a point-based manner and renders through rasterization. This methodology, in contrast to Radiance Fields that rely on ray tracing, demonstrates superior rendering quality and speed. However, the explicit and unstructured nature of 3D Gaussians poses a significant storage challenge, impeding its broader application. To address this challenge, we introduce the Gaussian-Forest modeling framework, which hierarchically represents a scene as a forest of hybrid 3D Gaussians. Each hybrid Gaussian retains its unique explicit attributes while sharing implicit ones with its sibling Gaussians, thus optimizing parameterization with significantly fewer variables. Moreover, adaptive growth and pruning strategies are designed, ensuring detailed representation in complex regions and a notable reduction in the number of required Gaussians. Extensive experiments demonstrate that Gaussian-Forest not only maintains comparable speed and quality but also achieves a compression rate surpassing 10 times, marking a significant advancement in efficient scene modeling. Codes will be available at https://github.com/Xian-Bei/GaussianForest.