HAC: 用于3D高斯泼溅压缩的哈希网格辅助上下文
HAC: Hash-grid Assisted Context for 3D Gaussian Splatting Compression
AI总结：
针对3D高斯泼溅点云稀疏无组织的压缩难题，提出哈希网格辅助上下文框架，结合二值哈希网格、自适应量化与掩码策略，实现超75倍压缩比且保真度更优，性能优于现有最优方法。
摘要：
3D高斯泼溅（3D Gaussian Splatting, 3DGS）已成为新视角合成领域极具前景的框架，具备渲染速度快、保真度高的优势。然而，海量高斯体及其关联属性需要高效的压缩技术支撑，但高斯点云（本文中称为锚点）的稀疏性与无组织特性为压缩带来了挑战。为解决该问题，我们利用无组织锚点与结构化哈希网格之间的关联，借助二者的互信息进行上下文建模，提出了哈希网格辅助上下文（Hash-grid Assisted Context, HAC）框架，以实现高度紧凑的3DGS表示。该方法引入二值哈希网格建立连续的空间一致性，通过精心设计的上下文模型揭示锚点的内在空间关联。为支持熵编码，我们采用高斯分布精准估计每个量化属性的概率，并提出自适应量化模块实现这些属性的高精度量化，以提升保真度恢复效果。此外，我们加入了自适应掩码策略以剔除无效高斯体和锚点。值得注意的是，本研究是首个探索基于上下文的3DGS表示压缩的工作，与原生3DGS相比体积缩减超75倍，同时提升了保真度，相较于当前最优（SOTA）3DGS压缩方法Scaffold-GS，体积缩减超11倍。我们的代码可通过以下链接获取：https://github.com/YihangChen-ee/HAC
英文摘要：
3D Gaussian Splatting (3DGS) has emerged as a promising framework for novel view synthesis, boasting rapid rendering speed with high fidelity. However, the substantial Gaussians and their associated attributes necessitate effective compression techniques. Nevertheless, the sparse and unorganized nature of the point cloud of Gaussians (or anchors in our paper) presents challenges for compression. To address this, we make use of the relations between the unorganized anchors and the structured hash grid, leveraging their mutual information for context modeling, and propose a Hash-grid Assisted Context (HAC) framework for highly compact 3DGS representation. Our approach introduces a binary hash grid to establish continuous spatial consistencies, allowing us to unveil the inherent spatial relations of anchors through a carefully designed context model. To facilitate entropy coding, we utilize Gaussian distributions to accurately estimate the probability of each quantized attribute, where an adaptive quantization module is proposed to enable high-precision quantization of these attributes for improved fidelity restoration. Additionally, we incorporate an adaptive masking strategy to eliminate invalid Gaussians and anchors. Importantly, our work is the pioneer to explore context-based compression for 3DGS representation, resulting in a remarkable size reduction of over $75\times$ compared to vanilla 3DGS, while simultaneously improving fidelity, and achieving over $11\times$ size reduction over SOTA 3DGS compression approach Scaffold-GS. Our code is available here: https://github.com/YihangChen-ee/HAC
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。
