GeoHCC: Local Geometry-Aware Hierarchical Context Compression for 3D Gaussian Splatting

2026-03-30

AI Summary

This work addresses the challenge of deploying 3D Gaussian Splatting (3DGS) due to its substantial storage overhead. Existing anchor-based compression methods often neglect geometric dependencies, leading to structural degradation and compromised rate-distortion performance. To overcome this, we propose a local geometry-aware compression framework that, for the first time, integrates geometric correlations throughout the entire compression pipeline. Our approach employs Neighborhood-Aware Anchor Pruning (NAAP) to evaluate and merge redundant anchors, and introduces a geometry-guided hierarchical entropy coding scheme coupled with a lightweight GG-Conv module to enable spatially adaptive context modeling. The method significantly enhances geometric integrity while maintaining superior rendering fidelity compared to state-of-the-art techniques, effectively breaking through the structural preservation bottleneck in 3DGS compression.

Technology Category

Computer Vision: 3D Computer VisionData Mining & Knowledge Management: Data CompressionKnowledge Representation and Reasoning: Geometric, Spatial, and Temporal Reasoning

Application Category

Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphsSearch and Retrieval-Augmented AI: Efficiency and scalability of Web search enginesUser Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation

Abstract

Although 3D Gaussian Splatting (3DGS) enables high-fidelity real-time rendering, its prohibitive storage overhead severely hinders practical deployment. Recent anchor-based 3DGS compression schemes reduce redundancy through context modeling, yet overlook explicit geometric dependencies, leading to structural degradation and suboptimal rate-distortion performance. In this paper, we propose GeoHCC, a geometry-aware 3DGS compression framework that incorporates inter-anchor geometric correlations into anchor pruning and entropy coding for compact representation. We first introduce Neighborhood-Aware Anchor Pruning (NAAP), which evaluates anchor importance via weighted neighborhood feature aggregation and merges redundant anchors into salient neighbors, yielding a compact yet geometry-consistent anchor set. Building upon this optimized structure, we further develop a hierarchical entropy coding scheme, in which coarse-to-fine priors are exploited through a lightweight Geometry-Guided Convolution (GG-Conv) operator to enable spatially adaptive context modeling and rate-distortion optimization. Extensive experiments demonstrate that GeoHCC effectively resolves the structure preservation bottleneck, maintaining superior geometric integrity and rendering fidelity over state-of-the-art anchor-based approaches.

Problem

• 3D Gaussian Splatting
• compression
• geometric dependencies
• anchor-based
• rate-distortion performance

Innovation

• Geometry-Aware Compression
• 3D Gaussian Splatting
• Anchor Pruning
• Hierarchical Entropy Coding
• Neighborhood Feature Aggregation