GS-SLAM: Dense Visual SLAM with 3D Gaussian Splatting
ShangHai JiAi Genetics & IVF Institute · Shanghai Artificial Intelligence Laboratory · +1 more institution
Abstract
In this paper, we introduce GS-SLAM that first utilizes 3D Gaussian representation in the Simultaneous Localization and Mapping (SLAM) system. It facilitates a better bal-ance between efficiency and accuracy. Compared to recent SLAM methods employing neural implicit representations, our method utilizes a real-time differentiable splatting ren-dering pipeline that offers significant speedup to map opti-mization and RGB-D rendering. Specifically, we propose an adaptive expansion strategy that adds new or deletes noisy 3D Gaussians in order to efficiently reconstruct new observed scene geometry and improve the mapping of pre-viously observed areas. This strategy is essential to ex-tend 3D Gaussian representation…
Citation impact
- FWCI
- 361.99
- Percentile
- 100%
- References
- 68
Authors
7- YCYan ChiCorresponding
ShangHai JiAi Genetics & IVF Institute, Shanghai Artificial Intelligence Laboratory
- DQDelin Qu
ShangHai JiAi Genetics & IVF Institute, Shanghai Artificial Intelligence Laboratory
- DXDan Xu
Hong Kong University of Science and Technology
- BZBin Zhao
ShangHai JiAi Genetics & IVF Institute, Shanghai Artificial Intelligence Laboratory
- ZWZhigang Wang
ShangHai JiAi Genetics & IVF Institute, Shanghai Artificial Intelligence Laboratory
Topics & keywords
- Computer science
- Artificial intelligence
- Computer vision
- Simultaneous localization and mapping
- Gaussian
- Computer graphics (images)
- Robot
- Mobile robot