PulseExploreJournal ClubDebatesTrendingResearchersJournals
Instagram
HomeExploreJournal ClubTrending
Synapse
⌘+K
Synapse
March 19, 20240 citationsOpen Access

High-Fidelity SLAM Using Gaussian Splatting with Rendering-Guided Densification and Regularized Optimization

View Full Paper
SSShuo SunMMMalcolm MielleALAchim J. Lilienthal

Key Points

Key points are not available for this paper at this time.

Abstract

We propose a dense RGBD SLAM system based on 3D Gaussian Splatting that provides metrically accurate pose tracking and visually realistic reconstruction. 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. 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.

Ask AI
Helpful
Bookmark
Share
View Full Paper

Cite This Study

Sun et al. (2024) studied this question.

synapsesocial.com/papers/68e73752b6db6435876b0488https://doi.org/10.48550/arxiv.2403.12535
Ask AI
Helpful
Bookmark
Share
View Full Paper

Also Consider

Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context:

  1. 1RD-SLAM: Real-Time Dense SLAM Using Gaussian Splatting2024 · 7 citations
  2. 2Splat-SLAM: Globally Optimized RGB-only SLAM with 3D Gaussians2024 · 3 citations
  3. 3RTG-SLAM: Real-time 3D Reconstruction at Scale using Gaussian Splatting2024 · 86 citations
  4. 4RP-SLAM: Real-Time Photorealistic SLAM With Efficient 3D Gaussian Splatting2025 · 4 citations
  5. 5MGS-SLAM: Monocular Sparse Tracking and Gaussian Mapping with Depth Smooth Regularization2024