面向3DGS压缩的非均匀量化
Non-Uniform Quantisation for 3DGS Compression
浏览论文内容
中文总结 AI 辅助
针对3D高斯溅射（3DGS）高比特率问题，本文提出适配其数据分布的非均匀量化方案，消除体素化后冗余，在基准数据集上实现最先进压缩性能，兼容点云表示，将为MPEG 3DGS压缩标准化提供正式贡献。
中文摘要 AI 辅助
3D高斯溅射（3DGS）已成为视图合成的强大技术，但其高比特率需求对存储和传输构成重大挑战。为实现实际应用并确保3DGS生态系统内的互操作性，标准化压缩格式至关重要。本文提出一种专为3DGS模型定制的新型非均匀量化方案，该方案通过应用重要性加权量化适应底层数据分布，并通过重要性加权合并消除体素化后冗余。在基准数据集上的广泛评估表明，所提方法达到了最先进的压缩性能，且该方案兼容任何基于点云的表示，旨在为即将开展的MPEG 3DGS压缩标准化活动提供正式贡献。
英文摘要
3D Gaussian Splatting (3DGS) has emerged as a powerful technique for novel view synthesis, yet its high bitrate requirements pose significant challenges for storage and transmission. To enable practical applications and ensure interoperability within the 3DGS ecosystem, standardised compression formats are essential. In this paper, we propose a novel non-uniform quantisation scheme specifically tailored for 3DGS models. Our approach adapts to the underlying data distribution by applying importance-weighted quantisation and eliminating post-voxelisation redundancy through importance weighted merging. Extensive evaluations on benchmark datasets demonstrate that our method achieves state-of-the-art compression performance. Furthermore, the proposed scheme is compatible with any point-cloud-based representation and is intended as a formal contribution to the upcoming MPEG 3DGS compression standardisation activities.
发表机构
- Vrije Universiteit Brussel（布鲁塞尔自由大学）
- Nokia（诺基亚公司）
机构由 AI 辅助整理，请以论文原文为准。
