HAC++: 迈向3D高斯溅射的100倍压缩
HAC++: Towards 100X Compression of 3D Gaussian Splatting
AI总结：
针对3D高斯溅射（3DGS）因大量高斯及属性导致的压缩挑战，提出HAC++，通过哈希网格上下文建模、锚点内关系捕捉、自适应量化与掩蔽策略，实现比原始3DGS超100倍压缩且提升保真度，性能优于Scaffold-GS。
摘要：
3D高斯溅射（3DGS）已成为新视角合成的有前景框架，具有高保真度和快速渲染速度。然而，大量高斯及其相关属性需要有效的压缩技术。但高斯点云（或本文中的锚点）的稀疏和无组织特性给压缩带来挑战。为实现紧凑尺寸，我们提出HAC++，它利用无组织锚点与结构化哈希网格之间的关系，通过互信息进行上下文建模。此外，HAC++捕捉锚点内的上下文关系以进一步提升压缩性能。为促进熵编码，我们利用高斯分布精确估计每个量化属性的概率，其中提出自适应量化模块以实现这些属性的高精度量化，从而改善保真度恢复。而且，我们引入自适应掩蔽策略以消除无效高斯和锚点。总体而言，HAC++在所有数据集上平均实现了比原始3DGS超过100倍的尺寸缩减，同时提升了保真度。它还实现了比Scaffold-GS超过20倍的尺寸缩减。我们的代码可在https://github.com/YihangChen-ee/HAC-plus获取。
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 achieve a compact size, we propose HAC++, which leverages the relationships between unorganized anchors and a structured hash grid, utilizing their mutual information for context modeling. Additionally, HAC++ captures intra-anchor contextual relationships to further enhance compression performance. To facilitate entropy coding, we utilize Gaussian distributions to precisely 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. Moreover, we incorporate an adaptive masking strategy to eliminate invalid Gaussians and anchors. Overall, HAC++ achieves a remarkable size reduction of over 100X compared to vanilla 3DGS when averaged on all datasets, while simultaneously improving fidelity. It also delivers more than 20X size reduction compared to Scaffold-GS. Our code is available at https://github.com/YihangChen-ee/HAC-plus.
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。
