Litcius/Paper detail

CGS-SLAM: Compact 3D Gaussian Splatting for Dense Visual SLAM

Tianchen Deng, Yaohui Chen, Jianfei Yang, Shenghai Yuan, Jiuming Liu, Danwei Wang, Weidong Chen

202511 citationsDOI

Abstract

Recent work has shown that 3D Gaussian-based SLAM enables high-quality reconstruction, accurate pose estimation, and real-time rendering of scenes. However, these approaches are built on a tremendous number of redundant 3D Gaussian ellipsoids, leading to high memory and storage costs and slow training speed. To address this limitation, we propose a compact 3D Gaussian Splatting SLAM system that reduces the number and the parameter size of Gaussian ellipsoids. A sliding window-based masking strategy is first proposed to reduce the redundant ellipsoids. Then, a novel geometry codebook-based quantization method is proposed to further compress 3D Gaussian geometric attributes. Robust and accurate pose estimation is achieved by a local-to-global bundle adjustment method with reprojection loss. Extensive experiments demonstrate that our method achieves faster training, rendering speed, and low memory usage while maintaining the state-of-the-art (SOTA) quality of the scene representation.

Topics & Concepts

Computer scienceArtificial intelligenceComputer visionGaussianRendering (computer graphics)Reprojection errorSimultaneous localization and mappingMixture modelRobustness (evolution)3d modelGaussian processAlgorithmQuantization (signal processing)PoseTraining setReal-time renderingBundle adjustmentGaussian filter3D reconstructionGeometric primitive3D renderingGaussian functionRobotics and Sensor-Based LocalizationAdvanced Vision and Imaging3D Shape Modeling and Analysis