用残差向量量化提升3D高斯点云压缩效率
SCAR-GS: Spatial Context Attention for Residuals in Progressive Gaussian Splatting
- 用残差向量量化替代传统标量量化，更好捕捉特征相关性
- 引入多分辨率哈希网格引导的自回归熵模型，提升编码效率
- 适合需高效压缩3D高斯点云的云渲染与流媒体应用
近期3D高斯点云拼贴技术实现了实时、高保真新视角合成。然而，这些模型在大中型场景下存储开销巨大，限制了其在云端和流媒体服务中的部署。现有渐进式压缩方法依赖渐进掩码与标量量化来降低高斯属性的比特率，但标量量化难以有效捕捉高维特征向量的相关性，可能制约率失真性能。本文提出一种新型渐进式编码器，以更强大的残差向量量化（Residual Vector Quantization）取代传统方法，用于压缩原始特征。核心贡献是基于多分辨率哈希网格引导的自回归熵模型，可精准预测每个后续传输索引的条件概率，从而实现粗粒度与精调层的高效压缩。
原文摘要 · Abstract (English)
Recent advances in 3D Gaussian Splatting have allowed for real-time, high-fidelity novel view synthesis. Nonetheless, these models have significant storage requirements for large and medium-sized scenes, hindering their deployment over cloud and streaming services. Some of the most recent progressive compression techniques for these models rely on progressive masking and scalar quantization techniques to reduce the bitrate of Gaussian attributes using spatial context models. While effective, scalar quantization may not optimally capture the correlations of high-dimensional feature vectors, which can potentially limit the rate-distortion performance. In this work, we introduce a novel progressive codec for 3D Gaussian Splatting that replaces traditional methods with a more powerful Residual Vector Quantization approach to compress the primitive features. Our key contribution is an auto-regressive entropy model, guided by a multi-resolution hash grid, that accurately predicts the conditional probability of each successive transmitted index, allowing for coarse and refinement layers to be compressed with high efficiency.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。