从散乱高斯到结构化映射：基于双阶段莫顿排序的高效高斯溅射编码

中文摘要 AI 辅助

三维高斯溅射（3DGS）能够实现高保真新视角合成，但其非结构化表示导致存储和带宽需求过大。为解决这一问题，基于投影的视频编码框架已成为主流方法，并得到MPEG正在进行的标准化工作的支持，该框架将3DGS属性转换为二维映射，以利用HEVC和VVC等成熟视频编解码器进行高效压缩。然而，该方法的有效性在很大程度上取决于投影视频的空间连贯性，而当前的排序策略（如PLAS和莫顿排序）未能充分保持这种连贯性，要么计算成本高昂，要么相关性保留有限。为克服这些局限，我们提出了一种双阶段莫顿空间排序算法，同时提升编码效率和处理速度。第一阶段，对高维属性应用基于莫顿的一维索引以增强空间局部性。第二阶段，通过结构化的二维莫顿映射表进一步优化布局连续性，该映射表强制空间邻接。这种分层策略生成高度规则、分块的特征图，具有强局部相关性，非常适合通过传统的基于块的编码工具进行压缩。实验结果表明，我们的方法在压缩性能和运行效率上均显著优于现有方法，为3DGS数据编码提供了一种实用且符合标准的解决方案。

英文摘要

3D Gaussian Splatting (3DGS) enables high fidelity novel view synthesis but suffers from excessive storage and bandwidth requirements due to its unstructured representation. To address this, a projection based video coding framework has emerged as a leading approach, supported by MPEG's ongoing standardization, where 3DGS attributes are converted into 2D maps to take advantage of efficient compression using established video codecs such as HEVC and VVC. However, the effectiveness of this approach depends heavily on the spatial coherence of the projected video, which current sorting strategies such as PLAS and Morton ordering fail to preserve adequately, either incurring high computational cost or achieving limited correlation retention. To overcome these limitations, we propose a dual phase Morton spatial sorting algorithm that improves both coding efficiency and processing speed. In the first phase, Morton based 1D indexing is applied to high dimensional attributes to enhance spatial locality. The second phase further refines layout continuity through a structured 2D Morton mapping table that enforces spatial adjacency. This hierarchical strategy generates highly regular, block wise feature maps with strong local correlation, making them well suited for compression via conventional block based coding tools. Experimental results show that our method significantly outperforms existing approaches in both compression performance and runtime efficiency, providing a practical and standard compatible solution for 3DGS data coding.

发表机构

• Fudan University（复旦大学）
• DAMO Academy, Alibaba Group（阿里巴巴集团达摩院）
• Hupan Lab（胡兰实验室）
• City University of Hong Kong（香港城市大学）

机构由 AI 辅助整理，请以论文原文为准。