MG-SLAM: Structure Gaussian Splatting SLAM with Manhattan World Hypothesis

Abstract

Gaussian Splatting SLAMs have made significant advancements in improving the efficiency and fidelity of real-time reconstructions. However, these systems often encounter incomplete reconstructions in complex indoor environments, characterized by substantial holes due to unobserved geometry caused by obstacles or limited view angles. To address this challenge, we present Manhattan Gaussian SLAM, an RGB-D system that leverages the Manhattan World hypothesis to enhance geometric accuracy and completeness. By seamlessly integrating fused line segments derived from structured scenes, our method ensures robust tracking in textureless indoor areas. Moreover, The extracted lines and planar surface assumption allow strategic interpolation of new Gaussians in regions of missing geometry, enabling efficient scene completion. Extensive experiments conducted on both synthetic and real-world scenes demonstrate that these advancements enable our method to achieve state-of-the-art performance, marking a substantial improvement in the capabilities of Gaussian SLAM systems.

IEEE Transactions on Automation Science and Engineering

References in corpus (7)

• ORB-SLAM: a Versatile and Accurate Monocular SLAM System
• ORB-SLAM2: an Open-Source SLAM System for Monocular, Stereo and RGB-D Cameras
• ORB-SLAM3: An Accurate Open-Source Library for Visual, Visual-Inertial and Multi-Map SLAM
• Differentiable Surface Splatting for Point-based Geometry Processing
• SGS-SLAM: Semantic Gaussian Splatting For Neural Dense SLAM
• NeSLAM: Neural Implicit Mapping and Self-Supervised Feature Tracking With Depth Completion and Denoising
• NGM-SLAM: Gaussian Splatting SLAM with Radiance Field Submap

Cited by in corpus (2)

• Incremental Joint Learning of Depth, Pose and Implicit Scene Representation on Monocular Camera in Large-scale Scenes
• DenseSplat: Densifying Gaussian Splatting SLAM with Neural Radiance Prior