HAC++: Towards 100X Compression of 3D Gaussian Splatting

TL;DR

HAC++ introduces a novel compression method for 3D Gaussian Splatting that significantly reduces data size by over 100X while maintaining or improving rendering fidelity, addressing the challenges of compressing unorganized point cloud data.

Contribution

HAC++ leverages relationships between unorganized anchors and structured hash grids, using mutual information and intra-anchor context to achieve unprecedented compression of 3D Gaussian Splatting data.

Findings

Over 100X size reduction compared to vanilla 3DGS

More than 20X size reduction compared to Scaffold-GS

Improved fidelity with high-precision quantization and adaptive masking

Abstract

3D Gaussian Splatting (3DGS) has emerged as a promising framework for novel view synthesis, boasting rapid rendering speed with high fidelity. However, the substantial Gaussians and their associated attributes necessitate effective compression techniques. Nevertheless, the sparse and unorganized nature of the point cloud of Gaussians (or anchors in our paper) presents challenges for compression. To achieve a compact size, we propose HAC++, which leverages the relationships between unorganized anchors and a structured hash grid, utilizing their mutual information for context modeling. Additionally, HAC++ captures intra-anchor contextual relationships to further enhance compression performance. To facilitate entropy coding, we utilize Gaussian distributions to precisely estimate the probability of each quantized attribute, where an adaptive quantization module is proposed to enable high-precision quantization of these attributes for improved fidelity restoration. Moreover, we incorporate an adaptive masking strategy to eliminate invalid Gaussians and anchors. Overall, HAC++ achieves a remarkable size reduction of over 100X compared to vanilla 3DGS when averaged on all datasets, while simultaneously improving fidelity. It also delivers more than 20X size reduction compared to Scaffold-GS. Our code is available at https://github.com/YihangChen-ee/HAC-plus.