High-Fidelity SLAM Using Gaussian Splatting with Rendering-Guided Densification and Regularized Optimization
INFORMATION
Authors: Shuo Sun, Malcolm Mielle, Achim J. Lilienthal, Martin Magnusson
Published in: 2024 IEEE International Conference on Intelligent Robots and Systems (IROS)
We propose a dense RGBD SLAM system based on 3D Gaussian Splatting that provides metrically accurate pose tracking and visually realistic reconstruction.
Method
To this end, we first propose a Gaussian densification strategy based on the rendering loss to map unobserved areas and refine reobserved areas.
Second, we introduce extra regularization parameters to alleviate the forgetting problem in the continuous mapping problem, where parameters tend to overfit the latest frame and result in decreasing rendering quality for previous frames.
Both mapping and tracking are performed with Gaussian parameters by minimizing re-rendering loss in a differentiable way.
Results
Compared to recent neural and concurrently developed gaussian splatting RGBD SLAM baselines, our method achieves state-of-the-art results on the synthetic dataset Replica and competitive results on the real-world dataset TUM.
What’s next
- Dense SLAM from Gaussian splatting still requires RGBD input; extending the rendering-guided densification to RGB-only or thermal settings is an open question — see SEAR for how we approach multi-modal reconstruction.
- The forgetting problem in continuous mapping is general: any online representation that over-parameterizes recent frames could benefit from similar regularization.