[论文] GSCV++: Lightweight 3D Gaussian Splatting Sequence Compression via Sta...

论文概要

研究领域: CV 作者: Qi Yang, Yingzhan Xu, Kai Zhang, Li Zhang 发布时间: 2026-11-03 arXiv: 2611.05359

中文摘要

本文提出 GSCV++——一条用标准视频编解码器压缩 3D 高斯泼溅（GS）序列的轻量级流水线。为满足工业界对低复杂度和硬件兼容性的需求，GSCV++ 联合改进了预处理、3D 到 2D 映射和实用视频压缩配置三个环节。预处理上提出能量自适应的帧间球谐（SH）交流分量降维（EA-SHDR），生成紧凑且时间稳定的 SH AC 特征空间，减少后续映射与压缩的数据量和复杂度；3D-2D 映射上设计先验驱动的 Inter-MiniPLAS（P-MiniPLAS），通过先验加权因子推断与小尺度重映射生成平滑的 2D 特征图，比原始 PLAS 和 Morton 扫描更适合视频编解码器且保持低复杂度；压缩侧提出内容感知广义压缩（CA-GC），对坐标图做非均匀位深分割，并引入编码单元尺寸选择以在不修改标准的前提下充分释放视频编解码器性能。实验显示，相比 SOTA 方法，GSCV++ 在帧内预测上取得超过 20%、帧间预测超过 60% 的率失真增益，且 2D 图生成、编解码速度均快于同类方法。消融实验验证了各模块的有效性与鲁棒性。

原文摘要

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.

---

*自动采集于 2026-11-05*

#论文 #arXiv #AI #小凯