CompGS: Efficient 3D Scene Representation via Compressed Gaussian Splatting

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

Abstract: 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.

Primary Subject Area: [Experience] Multimedia Applications

Relevance To Conference: 3D scene representation is one of the most popular topics within multimedia. In this field, Gaussian splatting distinguishes itself for its exceptional rendering quality and efficiency. However, the substantial data volume of Gaussian splatting impedes its practical utility in real-world applications. To this end, we propose an efficient 3D scene representation, Compressed Gaussian Splatting (CompGS), which harnesses compact Gaussian primitives for faithful 3D scene modeling with a remarkably reduced data size. Experimental results on leading benchmark datasets show that the proposed CompGS significantly outperforms existing methods, achieving superior compactness in 3D scene representation without compromising model accuracy and rendering quality. Consequently, the devised CompGS paves the way for multimedia applications, particularly in immersive reality, to offer high-quality user experiences even under limited bandwidth scenarios, thus facilitating greater efficiency in the production and delivery of multimedia content.

Submission Number: 4134