采用优化特征平面与标准视频编解码器的 3D Gaussian Splatting 压缩
Compression of 3D Gaussian Splatting with Optimized Feature Planes and Standard Video Codecs
AI总结：
针对 3D Gaussian Splatting 存储开销大的问题，提出结合渐进式三平面、频域熵建模和通道比特分配的压缩框架，利用标准视频编解码器提升率失真性能。
摘要：
3D Gaussian Splatting 是一种公认的三维场景表示方法，以高渲染质量和高速度著称。然而，其庞大的数据需求给实际应用带来了挑战。本文提出一种高效压缩技术，通过紧凑表示显著降低存储开销。我们提出一种统一架构，通过渐进式三平面结构结合点云数据与特征平面。该方法利用二维特征平面，实现连续的空间表示。为进一步优化这些表示，我们引入频域熵建模，该建模专为标准视频编解码器设计。我们还提出按通道的比特分配，以在比特率消耗与特征平面表示之间取得更好的权衡。因此，该模型利用标准、不可微的视频编解码器，有效利用特征平面内的空间相关性来提升率失真性能。实验结果表明，本方法在保持高渲染质量的同时，在数据紧凑性方面优于现有方法。项目页面位于 https://fraunhoferhhi.github.io/CodecGS。
英文摘要：
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
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。
