HPC: Hierarchical Point-based Latent Representation for Streaming Dynamic Gaussian Splatting Compression

2026-01-31

AI Summary

This work proposes the first end-to-end compression framework for dynamic Gaussian splatting to address its high memory footprint and significant redundancy in streaming scenarios. The method eliminates spatial redundancy by constructing a hierarchical point-based latent representation and, for the first time, models inter-frame correlations in neural network parameters. A tailored aggregation strategy is introduced to enable joint compression of geometry and appearance information. Experimental results demonstrate that, compared to the state-of-the-art, the proposed approach reduces storage overhead by 67% while preserving high-fidelity rendering quality, substantially improving the compression efficiency and compactness of dynamic Gaussian splatting.

Technology Category

• Data Mining & Knowledge Management: Data Compression
• Knowledge Representation and Reasoning: Geometric, Spatial, and Temporal Reasoning
• Machine Learning: Learning on the Edge & Model Compression

Application Category

• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Systems and Infrastructure for Web, Mobile and WoT: Data management and stream processing for Web, mobile and wireless applications
• Search and Retrieval-Augmented AI: Efficiency and scalability of Web search engines

Abstract

While dynamic Gaussian Splatting has driven significant advances in free-viewpoint video, maintaining its rendering quality with a small memory footprint for efficient streaming transmission still presents an ongoing challenge. Existing streaming dynamic Gaussian Splatting compression methods typically leverage a latent representation to drive the neural network for predicting Gaussian residuals between frames. Their core latent representations can be categorized into structured grid-based and unstructured point-based paradigms. However, the former incurs significant parameter redundancy by inevitably modeling unoccupied space, while the latter suffers from limited compactness as it fails to exploit local correlations. To relieve these limitations, we propose HPC, a novel streaming dynamic Gaussian Splatting compression framework. It employs a hierarchical point-based latent representation that operates on a per-Gaussian basis to avoid parameter redundancy in unoccupied space. Guided by a tailored aggregation scheme, these latent points achieve high compactness with low spatial redundancy. To improve compression efficiency, we further undertake the first investigation to compress neural networks for streaming dynamic Gaussian Splatting through mining and exploiting the inter-frame correlation of parameters. Combined with latent compression, this forms a fully end-to-end compression framework. Comprehensive experimental evaluations demonstrate that HPC substantially outperforms state-of-the-art methods. It achieves a storage reduction of 67% against its baseline while maintaining high reconstruction fidelity.

Problem

• dynamic Gaussian Splatting
• streaming compression
• latent representation
• memory footprint
• free-viewpoint video

Innovation

• hierarchical point-based representation
• dynamic Gaussian splatting
• streaming compression
• inter-frame parameter correlation
• end-to-end compression