Efficient spatial sorting boosts compression for 3D Gaussian data
From Scattered Gaussians to Structured Maps: Efficient Gaussian Splatting Coding via Dual-phase Morton Sorting
Multimedia
Summary
3D Gaussian Splatting is a way to create detailed 3D images but it requires a lot of storage and bandwidth. The authors found that converting these 3D data into 2D maps helps compress them better using video codecs. However, existing methods for arranging the data don't keep related points close together well, making compression less efficient. They designed a new two-phase sorting method that organizes data more neatly, improving both compression quality and processing speed.
What this means in practice
- •For 3d graphics developers: Compress 3D Gaussian spline representations more effectively for faster transmission and storage using standard video codecs.
- •For cloud streaming providers: Improve efficiency of delivering 3D rendered content by encoding 3DGS data into spatially coherent 2D maps for better bandwidth use.
Authors
Bolin Chen, Shanzhi Yin, Ru-Ling Liao, Yibo Fan, Yan Ye
Abstract
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.