GlORIE-SLAM: Globally Optimized RGB-only Implicit Encoding Point Cloud SLAM

TL;DR

GlORIE-SLAM introduces a neural point cloud-based RGB-only dense SLAM system that efficiently maintains global map and pose consistency without extensive backpropagation, leveraging a novel depth optimization layer and loop closure.

Contribution

The paper presents a novel neural point cloud scene representation and a DSPO layer for bundle adjustment in RGB-only SLAM, improving efficiency and accuracy.

Findings

Outperforms existing dense neural RGB SLAM methods in accuracy.

Achieves real-time performance with efficient scene representation.

Demonstrates robustness on multiple benchmark datasets.

Abstract

Recent advancements in RGB-only dense Simultaneous Localization and Mapping (SLAM) have predominantly utilized grid-based neural implicit encodings and/or struggle to efficiently realize global map and pose consistency. To this end, we propose an efficient RGB-only dense SLAM system using a flexible neural point cloud scene representation that adapts to keyframe poses and depth updates, without needing costly backpropagation. Another critical challenge of RGB-only SLAM is the lack of geometric priors. To alleviate this issue, with the aid of a monocular depth estimator, we introduce a novel DSPO layer for bundle adjustment which optimizes the pose and depth of keyframes along with the scale of the monocular depth. Finally, our system benefits from loop closure and online global bundle adjustment and performs either better or competitive to existing dense neural RGB SLAM methods in tracking, mapping and rendering accuracy on the Replica, TUM-RGBD and ScanNet datasets. The source code is available at https://github.com/zhangganlin/GlOIRE-SLAM