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

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zhang, Ganlin, Sandström, Erik, Zhang, Youmin, Patel, Manthan, Van Gool, Luc, Oswald, Martin R.
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909210852196352
author Zhang, Ganlin
Sandström, Erik
Zhang, Youmin
Patel, Manthan
Van Gool, Luc
Oswald, Martin R.
author_facet Zhang, Ganlin
Sandström, Erik
Zhang, Youmin
Patel, Manthan
Van Gool, Luc
Oswald, Martin R.
contents 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
format Preprint
id arxiv_https___arxiv_org_abs_2403_19549
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle GlORIE-SLAM: Globally Optimized RGB-only Implicit Encoding Point Cloud SLAM
Zhang, Ganlin
Sandström, Erik
Zhang, Youmin
Patel, Manthan
Van Gool, Luc
Oswald, Martin R.
Computer Vision and Pattern Recognition
Robotics
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
title GlORIE-SLAM: Globally Optimized RGB-only Implicit Encoding Point Cloud SLAM
topic Computer Vision and Pattern Recognition
Robotics
url https://arxiv.org/abs/2403.19549