Problem
Research questions and friction points this paper is trying to address.
3DGS
compression
bitrate
storage
transmission
Non-Uniform Quantisation for 3DGS Compression
๐ค AI Summary
ๆฌๆๆๅบไบไธ็ง้ๅฏน3D้ซๆฏ็นไบ๏ผ3DGS๏ผ็้ๅๅ้ๅๅ็ผฉๆนๆก๏ผ้่ฟ้่ฆๆงๅ ๆ้ๅๅๅๅนถๆถ้คๅไฝ๏ผ่งฃๅณไบ3DGSๅญๅจไธไผ ่พ็้ซๆฏ็น็้ฎ้ขใ
๐ Abstract
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.
Innovation
Methods, ideas, or system contributions that make the work stand out.
non-uniform quantisation
importance-weighted quantisation
post-voxelisation redundancy
3DGS compression
MPEG standardisation
๐ Similar Papers
2024-10-10arXiv.orgCitations: 2
