实现动态3D场景的细粒度可伸缩传输，支持低延迟自适应播放。
SplatStream: Fine Granular Scalable Gaussian Splatting for Adaptive 3D Scene Streaming
- 将3D高斯点云分层为质量和分辨率层级，支持多级编码。
- 引入跨层与时间预测，提升压缩效率，减少冗余数据。
- 按视觉重要性分包传输，关键点优先发送，适合带宽波动环境。
动态3D高斯点云（GS）实现了沉浸式媒体的高质量实时渲染，但其庞大的表示规模和帧间冗余给自适应流媒体传输带来挑战。本文提出SplatStream，一种面向动态3D场景传输的细粒度可伸缩高斯点云框架。该方法将GS场景分解为质量与分辨率层级，并引入层间预测编码实现可扩展性。在时序方向上，采用B帧实现时间质量可扩展性。设计轻量级跨层变换器预测器，用于跨层级与时间预测。此外，基于体素透明度的重要性度量，实现细粒度高斯点分包，使视觉重要点先行传输，支持渐进式重建。最终，可扩展的GS码流映射至MPEG-DASH兼容的子表示结构，可在带宽波动条件下实现细粒度、低延迟的动态高斯点云内容自适应传输。
原文摘要 · Abstract (English)
Dynamic 3D Gaussian Splatting (GS) enables high quality real-time rendering for immersive media, but its large representation size and frame-wise redundancy create significant challenges for adaptive streaming. This paper presents SplatStream, a fine granular scalable Gaussian splatting framework for dynamic 3D scene delivery. The proposed method decompose the GS scenes into quality and resolution layers, and introduces inter-layer predictive coding to achieve scalability. For temporal direction, B-frames are introduced to have temporal quality scalability. A lightweight cross-layer transformer based predictor is utilized for both cross layer and temporal predictions. In addition, a volume-opacity based importance measure is used for fine-grained Gaussian packetization, allowing visually important primitives to be transmitted earlier for progressive refinement. Finally, the scalable GS bitstream is mapped to an MPEG-DASH compatible sub-representation structure, enabling fine granular adaptive, low-latency delivery of dynamic Gaussian splatting content under bandwidth-varying conditions.
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。