Control Systems and Computers

Control Systems and Computers, 2024, Issue 2 (306), pp. 

UDC 004.932

A.O. SMIRNOV, PhD Student, Senior Researcher, International Research and Training Center for Information Technologies and Systems of the NAS and MES of Ukraine. ORCID: https://orcid.org/0009-0002-6509-4135,
40, Akademika Glushkova Avenue, Kyiv 03187, Ukraine, tonysmn97@gmail.com

DYNAMIC MAP MANAGEMENT FOR GAUSSIAN SPLATTING SLAM

Map representation and management for Simultaneous Localization and Mapping (SLAM) systems is at the core of such algorithms. Being able to efficiently construct new KeyFrames (KF), remove redundant ones, constructing covisibility graphs has direct impact on the performance and accuracy of SLAM. In this work we outline the algorithm for maintaining dynamic map and its management for SLAM algorithm based on Gaussian Splatting as the environment representation. Gaussian Splatting allows for high-fidelity photorealistic environment reconstruction using differentiable rasterization and is able to perform in real-time making it a great candidate for map representation in SLAM. Its end-to-end nature and gradient-based optimization significantly simplifies map optimization, camera pose estimation and KeyFrame management.

 Download full text! (On English)

Keywords: radiance fields, scientific computing, slam, bundle adjustment, gaussian splatting, differentiable rendering.

1. Carlos Campos et al. “ORB-SLAM3: An Accurate Open-Source Library for Visual, Visual–Inertial, and Multimap SLAM”. In: IEEE Transactions on Robotics 37.6 (Dec. 2021), pp. 1874¾ issn: 1941-0468. doi: 10.1109/tro.2021.3075644.
2. Yu Chen, Yisong Chen, and Guoping Wang. Bundle Adjustment Revisited. 2019. arXiv: 1912.03858 [cs.CV].
3. Bernhard Kerbl et al. 3D Gaussian Splatting for Real-Time Radiance Field Rendering. 2023. arXiv: 2308.04079 [cs.GR].
4. Diederik P. Kingma and Jimmy Ba. Adam: A Method for Stochastic Optimization. 2017. arXiv: 1412.6980 [cs.LG].
5. Kai Li Lim and Thomas Braunl. A Review of Visual Odometry Methods and Its Applications for Autonomous Driving. 2020. arXiv: 2009 . 09193 [cs.CV].
6. Ben Mildenhall et al. NeRF: Representing Scenes as Neural Radiance Fields for View Synthesis. 2020. arXiv: 2003.08934 [cs.CV].
7. Thomas Muller et al. “Instant neural graphics primitives with a multiresolution hash encoding”. In: ACM Transactions on Graphics 41.4 (July 2022), pp. 1¾ issn: 1557-7368. doi: 10.1145/3528223.3530127.
8. Raul Mur-Artal, J. M. M. Montiel, and Juan D. Tardos. “ORB-SLAM: A Versatile and Accurate Monocular SLAM System”. In: IEEE Transactions on Robotics 31.5 (Oct. 2015), pp. 1147–1163. issn: 1941-0468. doi: 10.1109/tro.2015.2463671.
9. Kerui Ren et al. Octree-GS: Towards Consistent Real-time Rendering with LOD-Structured 3D Gaussians. 2024. arXiv: 2403.17898 [cs.CV].
10. Qing Shuai et al. “Real-Time View Synthesis for Large Scenes with Millions of Square Meters”. In: 2024.
11. Julian Straub et al. The Replica Dataset: A Digital Replica of Indoor 2019. arXiv: 1906.05797 [cs.CV].
12. Sturm et al. “A Benchmark for the Evaluation of RGB-D SLAM Sys-tems”. In: Proc. of the International Conference on Intelligent Robot Sys-tems (IROS). Oct. 2012.

Received 15.03.2024