arXiv 2601.043482026-01cs.CVcs.GR

SCAR-GS：用于渐进高斯点扩散中残差的空间上下文注意力

SCAR-GS: Spatial Context Attention for Residuals in Progressive Gaussian Splatting

National University of Singapore（新加坡国立大学）；University of Deusto（德乌斯大学）

Diego Revilla, Pooja Suresh, Ooi Wei Tsang, Anand Bhojan

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

SCAR-GS通过残差向量量化和自回归熵模型提升3D高斯点扩散的压缩效率与率-失真性能。

摘要：

近年来，3D高斯点扩散技术的进步使得实时、高保真的新视角合成成为可能。然而，这些模型在处理大中型场景时具有显著的存储需求，限制了其在云服务和流媒体上的部署。一些最近的渐进压缩技术依赖于渐进掩码和标量量化技术，通过空间上下文模型来减少高斯属性的比特率。尽管有效，标量量化可能无法最佳捕捉高维特征向量的相关性，这可能限制了率-失真性能。在本文中，我们介绍了一种新的3D高斯点扩散渐进编码器，用更强大的残差向量量化方法来压缩基本特征。我们的关键贡献是基于多分辨率哈希网格的自回归熵模型，该模型能够准确预测每个依次传输索引的条件概率，使得粗略和细化层能够高效压缩。

英文摘要：

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.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。

AI总结：

摘要：

英文摘要：

相关论文