arXiv 2503.139482026-01-20cs.CV

Light4GS: 通过上下文模型实现轻量级紧凑的4D高斯点云生成

Light4GS: Lightweight Compact 4D Gaussian Splatting Generation via Context Model

School of Information Science and Electronic Engineering, Shanghai Jiao Tong University（信息科学与电子工程学院，上海交通大学）；School of Science and Engineering, University of Missouri–Kansas City（科学与工程学院，密苏里大学-堪萨斯城分校）；University of Chinese Academy of Sciences（中国科学院大学）

Mufan Liu, Qi Yang, He Huang, Wenjie Huang, Zhenlong Yuan, Zhu Li, Yiling Xu

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

Light4GS通过显著性剪枝和深度上下文模型实现轻量级4D高斯点云生成，提升压缩效率和渲染速度。

摘要：

3D高斯点云（3DGS）已作为一种高效且高保真的方法出现在新颖视角合成中。为了适应动态内容，可变形3DGS结合了时间可变形的原始体素和可学习的潜在嵌入来捕捉复杂的运动。尽管其表现令人印象深刻，但高维嵌入和大量的原始体素导致了显著的存储需求。在本文中，我们介绍了一种名为Light4GS的轻量级4DGS框架，该框架利用显著性剪枝与深度上下文模型，提供了一种轻量级且存储高效的动态3DGS表示。所提出的Light4GS基于4DGS，这是可变形3DGS的典型表示。具体而言，我们的框架基于两个核心组件：（1）一个时空显著性剪枝策略，该策略消除了超过64%的可变形原始体素，随后对剩余部分应用熵约束的球面谐波压缩；（2）一个深度上下文模型，该模型将内预测和外预测与超先验整合到一个由粗到细的上下文结构中，以实现高效的多尺度潜在嵌入压缩。我们的方法实现了超过120倍的压缩，并将渲染FPS提高了20%以上，同时优于帧级最先进的3DGS压缩方法，揭示了我们的Light4GS在内预测和外预测方法上的有效性，而不会牺牲渲染质量。

英文摘要：

3D Gaussian Splatting (3DGS) has emerged as an efficient and high-fidelity paradigm for novel view synthesis. To adapt 3DGS for dynamic content, deformable 3DGS incorporates temporally deformable primitives with learnable latent embeddings to capture complex motions. Despite its impressive performance, the high-dimensional embeddings and vast number of primitives lead to substantial storage requirements. In this paper, we introduce a \textbf{Light}weight \textbf{4}D\textbf{GS} framework, called Light4GS, that employs significance pruning with a deep context model to provide a lightweight storage-efficient dynamic 3DGS representation. The proposed Light4GS is based on 4DGS that is a typical representation of deformable 3DGS. Specifically, our framework is built upon two core components: (1) a spatio-temporal significance pruning strategy that eliminates over 64\% of the deformable primitives, followed by an entropy-constrained spherical harmonics compression applied to the remainder; and (2) a deep context model that integrates intra- and inter-prediction with hyperprior into a coarse-to-fine context structure to enable efficient multiscale latent embedding compression. Our approach achieves over 120x compression and increases rendering FPS up to 20\% compared to the baseline 4DGS, and also superior to frame-wise state-of-the-art 3DGS compression methods, revealing the effectiveness of our Light4GS in terms of both intra- and inter-prediction methods without sacrificing rendering quality.

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。