用进化树结构实现连续分层，让3D高斯点云流更高效、更平滑。
EvoGS: Constructing Continuous-Layered Gaussian Splatting with Evolution Tree for Scalable 3D Streaming
- 构建进化树式连续分层，通过父子精修机制生成细节。
- 减少65%以上点冗余，传输负载降低2.4倍，显存占用降5.5倍。
- 适合实时自适应3D流媒体，质量过渡自然无突变。
3D高斯点云的流式传输需要高度可扩展的渐进式表示。现有渐进方法依赖离散分层，为每级细节累积独立的点集，导致层间结构独立，引发误差累积、严重点冗余和质量过渡失控。本文提出EvoGS，首个连续分层表示，以进化树组织，通过显式的、类小波的父子精修机制生成更细粒度细节。该设计使子节点能结构化修正父节点误差，生成本质稀疏且高度可压缩的层间信号。大量实验表明，EvoGS将点冗余从超过65%降至不足25%。相比最先进基线，其传输负载降低最多2.4倍，GPU显存占用减少最多5.5倍，并实现最优的实时自适应流媒体所需的平滑质量过渡。
原文摘要 · Abstract (English)
Streaming 3D Gaussian Splatting requires highly scalable, progressive representations. Existing progressive methods rely on \textit{discrete layering}, accumulating separate splat sets for each level of detail. This structural independence between layers inherently leads to error accumulation, severe splat redundancy, and uncontrolled quality transitions. We propose EvoGS, the first \textit{continuous-layering} representation. Organized as an Evolution Tree, EvoGS generates finer details via an explicit, wavelet-inspired parent-child refinement. This empowers child nodes to structurally correct ancestral errors, yield inherently sparse and highly compressible inter-layer signals. Extensive experiments show EvoGS eliminates splat redundancy from over 65\% to under 25\%. Compared to state-of-the-art baselines, it reduces transmission payload and GPU VRAM footprint by up to 2.4$\times$ and 5.5$\times$, respectively, and achieves smooth quality transitions optimal for real-time adaptive streaming. Project page: https://yuang-ian.github.io/evogs/
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。