Skip to content

G 2 -SLAM: Geometrically-guided 3D Gaussian Splatting SLAM via robust loop validation and anisotropic shaping

Oct 2026 · Measurement science and technology · 0 citations

TL;DR

G²-SLAM is presented, a geometry-guided monocular 3DGS SLAM system that combines depth-Hessian-based loop validation with Hessian-direction-conditioned, image-edge-aware depth regularization, and the online tracking component reaches workstation-level frame rates.

Abstract

Monocular 3D Gaussian Splatting (3DGS) SLAM estimates camera motion and dense scene appearance from a single RGB stream, but sparse views make both estimates sensitive to depth uncertainty and false loop closures. We present G²-SLAM, a geometry-guided monocular 3DGS SLAM system that combines depth-Hessian-based loop validation with Hessian-direction-conditioned, image-edge-aware depth regularization. The loop module adds a second-order geometric consistency test before Sim(3) optimization, while the regularizer suppresses intra-region depth fluctuations without strongly smoothing across structural boundaries or requiring pseudo-camera rendering. On Replica, G²-SLAM remains competitive with strong dense SLAM baselines in a high-quality synthetic setting. Across six selected LLFF scenes, it improves the average PSNR from 26.05 to 26.55 dB over HI-SLAM2; on the 27-image room scene, the maximum per-scene gain is 0.86 dB. A short-duration RTK-GPS outdoor study provides a proof-of-concept evaluation under real-world motion. The online tracking component reaches workstation-level frame rates, whereas full global refinement remains offline and is not intended for real-time edge deployment. The project page and public code snapshot are available at https://github.com/galahies/G--SLAM.

View source

Similar papers

Open access Oct 2026

MoGe2-SLAM: Outdoor Monocular 3D Gaussian Splatting SLAM with Absolute Scale

MoGe2-SLAM is competitive with existing monocular SLAM baselines in trajectory shape and novel-view fidelity while recovering trajectories and Gaussian maps in an approximate physical scale under the stated camera-height prior.

Jia-En Zhao, Jin-Ming Zhang, Bi-Qing Li et al. · 0 citations
Oct 2026

Gradient-Driven Point Allocation for Depth-Guided 3D Gaussian Splatting in Indoor Scenes

A lightweight gradient-driven point allocation strategy for depth-guided Gaussian splatting that bypasses traditional Structure-from-Motion initialization and incorporates a bidirectional re-projection check to eliminate transient noise and occlusions, ensuring geometric consistency is proposed.

Yu-Hao Shang, Zhen-Shen Qu, Guan-Yi Rong et al. · 0 citations
Preprint Nov 2026

DASH-SLAM: Calibration-Free Metric Monocular SLAM via Depth Scale Propagation

Geometric foundation models estimate dense geometry and camera parameters from monocular images, but reliable SLAM also requires consistent scale and accurate data association across successive reconstructions. We present DASH-SLAM, a monocular SLAM system that integrates metric depth predictions from pretrained Depth...

Otavio Ribas, Jacopo Panerati, Pierre-Yves Lajoie · 0 citations
Book Open access Nov 2026

M3: Dense Matching Meets Multi-View Foundation Models for Monocular Gaussian Splatting SLAM

Streaming reconstruction from uncalibrated monocular video remains challenging, as it requires both high-precision pose estimation and computationally efficient online refinement in dynamic environments. While coupling 3D foundation models with SLAM frameworks is a promising paradigm, a critical bottleneck persists: mo...

Ke-Rui Ren, Guang-Hao Li, Chang-Jian Jiang et al. · 0 citations
Preprint Nov 2026

GEMOR-GS: Global Extrinsic-calibration-refined Mapping and Online Relocalization for 3D Gaussian-Splatting SLAM

Photorealistic and metrically consistent world representations are a primary requirement for LiDAR--inertial--visual SLAM systems that serve robots over continuous operation. 3D Gaussian splatting makes such representations attainable by supplying an explicit, renderable, and queryable scene model. We present GEMOR-GS...

Yu-Chen Yang, Ming Ding, Xin'ao Wu et al. · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.