REVIEW 6 cited by
Splat-SLAM: Globally Optimized RGB-only SLAM with 3D Gaussians
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
3D Gaussian Splatting has emerged as a powerful representation of geometry and appearance for RGB-only dense Simultaneous Localization and Mapping (SLAM), as it provides a compact dense map representation while enabling efficient and high-quality map rendering. However, existing methods show significantly worse reconstruction quality than competing methods using other 3D representations, e.g. neural points clouds, since they either do not employ global map and pose optimization or make use of monocular depth. In response, we propose the first RGB-only SLAM system with a dense 3D Gaussian map representation that utilizes all benefits of globally optimized tracking by adapting dynamically to keyframe pose and depth updates by actively deforming the 3D Gaussian map. Moreover, we find that refining the depth updates in inaccurate areas with a monocular depth estimator further improves the accuracy of the 3D reconstruction. Our experiments on the Replica, TUM-RGBD, and ScanNet datasets indicate the effectiveness of globally optimized 3D Gaussians, as the approach achieves superior or on par performance with existing RGB-only SLAM methods methods in tracking, mapping and rendering accuracy while yielding small map sizes and fast runtimes. The source code is available at https://github.com/eriksandstroem/Splat-SLAM.
Forward citations
Cited by 6 Pith papers
-
ReMoSPLAT: Reactive Mobile Manipulation Control on a Gaussian Splat
ReMoSPLAT achieves reactive mobile-manipulation collision avoidance by querying distances from a Gaussian Splat reconstruction, matching a ground-truth-SDF controller in simulation.
-
NSL-SLAM: High-Fidelity Neural Structured-Light Depth for Practical SLAM and Reconstruction
Injecting frozen monocular depth features into neural structured-light decoding cuts Replica-SL depth RMSE ~35% vs NSL and, with depth-centric GICP+sparse anchors+light BA, yields the most stable real D435 SLAM among ...
-
GLidE-SLAM: GL-Accelerated Indirect-Direct Embedded SLAM
GLidE-SLAM moves pose-only photometric tracking to OpenGL ES compute shaders, reporting up to 9x faster frame rates than ORB-SLAM2 on embedded platforms with comparable ATE on TUM and EuRoC sequences.
-
Online 3D Gaussian Splatting Modeling with Novel View Selection
During online Gaussian splatting SLAM, training extra on non-keyframes that view the most uncertain Gaussians improves model completeness over keyframe-only training.
-
Outdoor Monocular SLAM with Global Scale-Consistent 3D Gaussian Pointmaps
S3PO-GS uses the 3DGS-rendered pointmap as the scale anchor for pose estimation and patch-aligns pretrained pointmaps to map scale, improving outdoor monocular 3DGS SLAM tracking and rendering.
-
Reconstructing 4D Spatial Intelligence: A Survey
A review that classifies 4D scene reconstruction methods into five progressive levels: low-level cues, scene components, dynamic scenes, interactions, and physics.
Discussion (0). Sign in to comment.