发表机构
Xiaomi Technology Netherlands B.V（小米科技荷兰有限公司）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
该研究提出TSOG格式，扩展SOG框架至时间域以高效表示4DGS内容，经评估其文件大小缩减超90%且质量下降极小，可实现动态4D内容的高效存储与传输。
AI 中文摘要
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将空间有序高斯（SOG）框架扩展至时间域，引入时间线属性并对几何与外观属性进行时间参数化。与SOG类似，TSOG为有损格式，为每个高斯分配唯一索引并将属性值编码为索引对齐的图像数据。TSOG与模型无关、可扩展，且兼容离散与连续的4DGS表示。以PLY序列和FreeTimeGS（分别作为简单及最先进的4DGS表示）为基准的评估显示，其文件大小缩减超90%，PSNR差异介于-0.42至+0.85 dB之间。这些结果表明，TSOG可在极小质量下降的情况下实现大幅文件大小节省，为下一代4D内容实现动态场景的高效表示、存储与传输。
英文摘要
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.
Comments2026 IEEE International Conference on Image Processing (ICIP). IEEE, 2026
