Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

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

About

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

Ganlin Zhang, Erik Sandstr\"om, Youmin Zhang, Manthan Patel, Luc Van Gool, Martin R. Oswald• 2024

Related benchmarks

TaskDatasetResultRank
Visual OdometryTUM-RGBD
freiburg1/xyz Error1.2
34
Monocular Visual OdometryVIVID Mean over sequences
ATE RMSE0.37
20
Monocular Visual OdometryVIVID in_rob_local
ATE RMSE0.06
18
Monocular Visual OdometryVIVID in_rob_global
ATE RMSE0.08
17
Monocular Visual OdometryVIVID in_unst_local
ATE RMSE0.04
17
Monocular Visual OdometryVIVID in_rob_dark
ATE RMSE0.07
16
Monocular Visual OdometryVIVID in_unst_global
ATE RMSE0.06
15
RenderingTUM-RGBD fr2 xyz
PSNR25.62
14
Monocular Visual OdometryVIVID in_agg_global
ATE RMSE0.08
14
RenderingTUM-RGBD fr3 office
PSNR21.21
14
Showing 10 of 18 rows

Other info

Follow for update