Lightweight 3D Gaussian splatting compression improves video codec efficiency
GSCV++: Lightweight 3D Gaussian Splatting Sequence Compression via Standard Video Codecs
Computer Vision and Pattern Recognition
Summary
Compressing 3D Gaussian splatting sequences, which represent 3D scenes as many small blurry blobs, is challenging due to their size and complexity. The authors developed GSCV++, a pipeline that reduces data size and speeds up processing by carefully transforming 3D data into 2D maps optimized for video compression. Their method uses adaptive techniques to remove redundant details, arranges data to match video codecs better, and adjusts compression settings to balance quality and speed. Experiments show GSCV++ compresses better and faster than previous methods while preserving visual quality.
What this means in practice
- •For 3d graphics developers: Compress and stream 3D Gaussian splatting sequences efficiently using standard video codecs, reducing file size and decoding time without special hardware.
- •For video streaming engineers: Integrate compressed 3D splatting data into existing video pipelines to deliver interactive 3D content with manageable bandwidth costs.
Authors
Qi Yang, Yingzhan Xu, Kai Zhang, Li Zhang
Abstract
This paper presents GSCV++, a lightweight pipeline for 3D {G}aussian {S}platting (GS) sequences {C}ompression with standard {V}ideo codecs. To meet the requirements of low-complexity and hardware compatibility from the industry, GSCV++ jointly improves preprocessing, 3D-to-2D mapping, and practical video compression configuration of GS compression. First, for preprocessing, energy-adaptive inter-frame spherical harmonic (SH) alternative current (AC) dimensionality reduction (EA-SHDR) is proposed to produces a compact and stable temporal SH AC feature space. It can reduce the data volume of following mapping and practical compression, as well as less complexity while eliminating redundant information. Second, for 3D-to-2D mapping, prior-based Inter-MiniPLAS (P-MiniPLAS) is designed to generate smooth 2D feature maps through prior-based weighting factor inference and small scale remapping. Compared with vanilla Parallel Linear Assignment Sorting (PLAS) and Morton scan, P-MiniPLAS ensures the generated 2D maps are more suitable for the video codec while maintaining a low level of computational complexity. Third, for practical compression, content-aware generalized compression (CA-GC) is developed to use a non-uniform bit-depth split for coordinate map generation, and a coding unit size selection is introduced for efficient compression complexity control, which fully exploits the performance of video codecs without involving normative changes. Experiments demonstrate that GSCV++ reports over 20\% in intra- and 60\% in inter-prediction rate-distortion gains compared with state-of-the-art (SOTA) methods. GSCV++ also achieves faster 2D map generation, encoding, and decoding than other SOTA methods using the same type of video codecs. Ablation studies verify the effectiveness and robustness of the proposed modules and provide insights for subsequent research.