一种新型4D内容压缩格式，可大幅减小动态场景文件体积。
TSOG: A Format For Temporally And Spatially Ordered Gaussians
- 将高斯点按时空顺序编码，用索引映射属性数据。
- 相比现有方法，文件大小减少超90%，画质损失极小（PSNR波动±0.85dB）。
- 适用于各类4D高斯溅射模型，适合高效存储与传输动态3D内容。
我们提出时空有序高斯（TSOG），一种用于高效表示4D高斯溅射（4DGS）内容的格式。TSOG通过引入时间轴属性和几何与外观属性的时序参数化，将空间有序高斯（SOG）框架扩展至时间维度。与SOG类似，TSOG是一种有损格式，为每个高斯点分配唯一索引，并将属性值编码为对齐索引的图像数据。TSOG具有模型无关性、可扩展性，并兼容离散与连续的4DGS表示。在PLYs序列和FreeTimeGS作为基线（分别代表简单与前沿4DGS表示）的评估中，文件大小减少超过90%，PSNR差异在-0.42至+0.85 dB之间。结果表明，在几乎无质量损失的前提下实现了显著的文件压缩，适用于下一代4D内容的高效表示、存储与传输。
原文摘要 · Abstract (English)
We propose Temporally and Spatially Ordered Gaussians (TSOG), a format for efficient representation of 4D Gaussian Splatting (4DGS) content. TSOG extends the Spatially Ordered Gaussians (SOG) framework to the temporal domain by introducing a timeline attribute and temporal parameterization of geometry and appearance attributes. Similar to SOG, TSOG is a lossy format that assigns each Gaussian a unique index and encodes attribute values as index-aligned image data. TSOG is model-agnostic, extensible, and compatible with both discrete and continuous 4DGS representations. Evaluation using a PLYs sequence and FreeTimeGS as baselines, serving as simplistic and state-of-the-art 4DGS representations respectively, shows file size reductions exceeding 90%, with PSNR differences ranging between -0.42 and +0.85 dB. These results demonstrate substantial file size savings with minimal quality degradation, enabling efficient representation, storage, and delivery of dynamic scenes for next-generation 4D content.
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。