arXiv 2602.006712026-01-31cs.CV

HPC: 基于层次点表示的流式动态高斯点云压缩

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

MoE Key Laboratory of Brain-inspired Intelligent Perception and Cognition, University of Science and Technology of China（脑启发式智能感知与认知联合实验室，中国科学技术大学）；University of Missouri, Kansas City（密苏里大学，堪萨斯城）

Yangzhi Ma, Bojun Liu, Wenting Liao, Dong Liu, Zhu Li, Li Li

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

HPC提出了一种基于层次点表示的流式动态高斯点云压缩框架，通过减少参数冗余和利用帧间相关性，实现了高效压缩和高保真重建。

摘要：

尽管动态高斯点云技术在自由视角视频中推动了显著进展，但如何在小内存 footprint 下维持渲染质量以实现高效流式传输仍是一个持续挑战。现有的流式动态高斯点云压缩方法通常利用潜在表示来驱动神经网络预测帧间高斯残差。其核心潜在表示可以分为结构化网格基和非结构化点基两种范式。然而，前者由于不可避免地建模空闲空间而带来显著的参数冗余，后者则由于无法利用局部相关性而存在有限的紧凑性。为缓解这些限制，我们提出HPC，一种新的流式动态高斯点云压缩框架。它采用基于每个高斯的层次点表示，以避免空闲空间中的参数冗余。通过定制的聚合方案引导，这些潜在点在低空间冗余下实现高紧凑性。为进一步提高压缩效率，我们进一步开展了首次研究，通过挖掘和利用参数的帧间相关性来压缩流式动态高斯点云的神经网络。结合潜在压缩，这形成了一个完全端到端的压缩框架。全面的实验评估表明，HPC显著优于最先进的方法。它在保持高重建保真度的同时，相对于基线实现了67%的存储减少。

英文摘要：

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.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。