CompGS: Efficient 3D Scene Representation via Compressed Gaussian Splatting
This addresses the practical utility issue for applications requiring efficient 3D scene representation, but it is incremental as it builds upon existing Gaussian splatting techniques.
The paper tackles the problem of high data volume in Gaussian splatting for 3D scene representation by proposing Compressed Gaussian Splatting (CompGS), which uses compact Gaussian primitives and a hybrid structure to reduce data size while maintaining accuracy and rendering quality, achieving superior compactness compared to existing methods.
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.