CompGS：通过压缩高斯飘粒实现高效的3D场景表示

CompGS: Efficient 3D Scene Representation via Compressed Gaussian Splatting

April 15, 2024

作者: Xiangrui Liu, Xinju Wu, Pingping Zhang, Shiqi Wang, Zhu Li, Sam Kwong

cs.AI

摘要

高斯飘逸（Gaussian splatting）以其出色的渲染质量和效率而闻名，在3D场景表示中已成为一种突出的技术。然而，高斯飘逸的大量数据量阻碍了其在实际应用中的实用性。在本文中，我们提出了一种高效的3D场景表示，名为压缩高斯飘逸（CompGS），它利用紧凑的高斯基元进行忠实的3D场景建模，同时大大减少了数据大小。为确保高斯基元的紧凑性，我们设计了一种捕捉彼此之间预测关系的混合基元结构。然后，我们利用一小组锚定基元进行预测，使大多数基元被封装为高度紧凑的残差形式。此外，我们开发了一种受速率约束的优化方案，以消除这种混合基元中的冗余，引导我们的CompGS朝着比特率消耗和表示效果之间的最佳折衷方向发展。实验结果表明，所提出的CompGS明显优于现有方法，在不影响模型准确性和渲染质量的情况下，实现了3D场景表示的卓越紧凑性。我们的代码将在GitHub上发布供进一步研究使用。

English

Gaussian splatting, renowned for its exceptional rendering quality and efficiency, has emerged as a prominent technique in 3D scene representation. However, the substantial data volume of Gaussian splatting impedes its practical utility in real-world applications. Herein, we propose an efficient 3D scene representation, named Compressed Gaussian Splatting (CompGS), which harnesses compact Gaussian primitives for faithful 3D scene modeling with a remarkably reduced data size. To ensure the compactness of Gaussian primitives, we devise a hybrid primitive structure that captures predictive relationships between each other. Then, we exploit a small set of anchor primitives for prediction, allowing the majority of primitives to be encapsulated into highly compact residual forms. Moreover, we develop a rate-constrained optimization scheme to eliminate redundancies within such hybrid primitives, steering our CompGS towards an optimal trade-off between bitrate consumption and representation efficacy. Experimental results show that the proposed CompGS significantly outperforms existing methods, achieving superior compactness in 3D scene representation without compromising model accuracy and rendering quality. Our code will be released on GitHub for further research.