用视频编码器压缩3D高斯点云，大幅降低存储体积。
Compression of 3D Gaussian Splatting with Optimized Feature Planes and Standard Video Codecs
- 用分层三平面结构融合点云与特征图，实现连续空间表示。
- 在频域建模熵并自适应分配通道比特，提升压缩效率。
- 兼容标准视频编码器，适合需要高效传输的3D场景应用。
3D高斯点云是公认的3D场景表示方法，以高质量渲染和高速度著称。然而其巨大的数据量给实际应用带来挑战。本文提出一种高效的压缩技术，通过紧凑表示显著降低存储开销。我们设计统一架构，将点云数据与特征平面结合，采用渐进式三平面结构。利用2D特征平面实现连续空间表达，并在频域引入熵建模，专为标准视频编码器优化。同时提出通道级比特分配策略，平衡码率与特征平面表现。结果表明，该方法有效利用特征平面内的空间相关性，借助非可微的标准视频编码器提升率失真性能。实验显示，在保持高渲染质量的前提下，本方法在数据紧凑性上优于现有技术。
原文摘要 · Abstract (English)
3D Gaussian Splatting is a recognized method for 3D scene representation, known for its high rendering quality and speed. However, its substantial data requirements present challenges for practical applications. In this paper, we introduce an efficient compression technique that significantly reduces storage overhead by using compact representation. We propose a unified architecture that combines point cloud data and feature planes through a progressive tri-plane structure. Our method utilizes 2D feature planes, enabling continuous spatial representation. To further optimize these representations, we incorporate entropy modeling in the frequency domain, specifically designed for standard video codecs. We also propose channel-wise bit allocation to achieve a better trade-off between bitrate consumption and feature plane representation. Consequently, our model effectively leverages spatial correlations within the feature planes to enhance rate-distortion performance using standard, non-differentiable video codecs. Experimental results demonstrate that our method outperforms existing methods in data compactness while maintaining high rendering quality. Our project page is available at https://fraunhoferhhi.github.io/CodecGS
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。