LoD结构的3D高斯点云法对于流媒体视频重建
LoD-Structured 3D Gaussian Splatting for Streaming Video Reconstruction
AI总结：
本文提出StreamLoD-GS框架，通过LoD结构、运动分区和量化残差细化技术，实现流媒体视频的高效重建与高保真渲染。
摘要：
自由视角视频（FVV）重建能够实现逼真且交互式的3D场景可视化；然而，实时流媒体常常受到稀疏视角输入、训练成本高和带宽限制的阻碍。尽管最近的3D高斯点云法（3DGS）因渲染速度快而推动了FVV的发展，但流媒体自由视角视频（SFVV）引入了额外的需求：快速优化、在稀疏约束下实现高保真重建以及最小的存储足迹。为弥合这一差距，我们提出StreamLoD-GS，一种基于LoD的高斯点云框架，专门用于SFVV。我们的方法集成了三个核心创新：1）基于锚点和八叉树的LoD结构3DGS，结合分层高斯丢弃技术，以确保高效且稳定的优化，同时保持高质量的渲染；2）基于GMM的运动分区机制，将动态和静态内容分开，细化动态区域的同时保持背景稳定性；3）量化残差细化框架，显著降低存储需求，而不会牺牲视觉保真度。大量实验表明，StreamLoD-GS在质量和效率以及存储方面实现了竞争性或最先进性能。
英文摘要：
Free-Viewpoint Video (FVV) reconstruction enables photorealistic and interactive 3D scene visualization; however, real-time streaming is often bottlenecked by sparse-view inputs, prohibitive training costs, and bandwidth constraints. While recent 3D Gaussian Splatting (3DGS) has advanced FVV due to its superior rendering speed, Streaming Free-Viewpoint Video (SFVV) introduces additional demands for rapid optimization, high-fidelity reconstruction under sparse constraints, and minimal storage footprints. To bridge this gap, we propose StreamLoD-GS, an LoD-based Gaussian Splatting framework designed specifically for SFVV. Our approach integrates three core innovations: 1) an Anchor- and Octree-based LoD-structured 3DGS with a hierarchical Gaussian dropout technique to ensure efficient and stable optimization while maintaining high-quality rendering; 2) a GMM-based motion partitioning mechanism that separates dynamic and static content, refining dynamic regions while preserving background stability; and 3) a quantized residual refinement framework that significantly reduces storage requirements without compromising visual fidelity. Extensive experiments demonstrate that StreamLoD-GS achieves competitive or state-of-the-art performance in terms of quality, efficiency, and storage.
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。
