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

arXiv:2403.19549v1 Announce Type: new
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 …

abstract arxiv cloud cs.cv cs.ro encoding global grid localization map mapping representation slam struggle type