Compression of 3D Gaussian Splatting with Optimized Feature Planes and Standard Video Codecs

TL;DR

This paper presents a novel compression method for 3D Gaussian Splatting that combines feature plane optimization and standard video codecs, significantly reducing data size while preserving rendering quality.

Contribution

It introduces a unified architecture with frequency domain entropy modeling and channel-wise bit allocation for efficient 3D scene data compression.

Findings

Outperforms existing methods in data compactness

Maintains high rendering quality with reduced storage

Leverages spatial correlations for better rate-distortion trade-off

Abstract

3D Gaussian Splatting is a recognized method for 3D scene representation, known for its high rendering quality and speed. However, its substantial data requirements present challenges for practical applications. In this paper, we introduce an efficient compression technique that significantly reduces storage overhead by using compact representation. We propose a unified architecture that combines point cloud data and feature planes through a progressive tri-plane structure. Our method utilizes 2D feature planes, enabling continuous spatial representation. To further optimize these representations, we incorporate entropy modeling in the frequency domain, specifically designed for standard video codecs. We also propose channel-wise bit allocation to achieve a better trade-off between bitrate consumption and feature plane representation. Consequently, our model effectively leverages spatial correlations within the feature planes to enhance rate-distortion performance using standard, non-differentiable video codecs. Experimental results demonstrate that our method outperforms existing methods in data compactness while maintaining high rendering quality. Our project page is available at https://fraunhoferhhi.github.io/CodecGS