GS-SLAM: Dense Visual SLAM with 3D Gaussian Splatting
By Chi Yan, Delin Qu, Dong Wang, Dan Xu, Zhigang Wang, Bin Zhao, Xuelong Li. Computer Vision and Pattern Recognition, 2023
497 citations recorded by the source corpus.
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 to reconstruct the whole scene rather than synthesize a static object in existing meth-ods. Moreover, in the pose tracking process, an effective coarse-to-fine technique is designed to select reliable 3D Gaussian representations to optimize camera pose, resulting in runtime reduction and robust estimation. Our method achieves competitive performance compared with existing state-of-the-art real-time methods on the Replica, TUM-RGBD datasets. Project page: https://gs-slam.github.io/.
Subfields: Aerospace Engineering, Computer Vision and Pattern Recognition
View Paper: https://www.semanticscholar.org/paper/8b5f4902411123c5e68ded502f296cf325864831
Citations in the corpus
- A Survey on 3D Gaussian Splatting (2024, unknown): “EndoGaussian [138] introduced two new strategies: holistic Gaussian initialization for dense initialization and spatiotemporal Gaussian tracking for modeling surface dynamics.”
- Aligning Cyber Space With Physical World: A Comprehensive Survey on Embodied AI (2024, unknown): “Embodiedperceptionrequires visualperceptionandreasoning,understandingthe3-Drelations within a scene, and predicting and performing complex tasks based on visual information.”
- Recent advances in 3D Gaussian splatting (2024, unknown): “GS-SLAM [115] proposes an adaptive 3D Gaussian expanding strategy to add new 3D Gaussians into the training stage and delete unreliable ones with captured depths and rendered opacity values.”