paper-with-me

Papers

Gaussian-SLAM: Photo-realistic Dense SLAM with Gaussian Splatting

2023-12-06 · Vladimir Yugay, Yue Li, Theo Gevers, Martin R. Oswald

We present a dense simultaneous localization and mapping (SLAM) method that uses 3D Gaussians as a scene representation. Our approach enables interactive-time reconstruction and photo-realistic rendering from real-world single-camera RGBD videos. To this end, we propose a novel effective strategy for seeding new Gaussians for newly explored areas and their effective online optimization that is independent of the scene size and thus scalable to larger scenes. This is achieved by organizing the scene into sub-maps which are independently optimized and do not need to be kept in memory. We further accomplish frame-to-model camera tracking by minimizing photometric and geometric losses between the input and rendered frames. The Gaussian representation allows for high-quality photo-realistic real-time rendering of real-world scenes. Evaluation on synthetic and real-world datasets demonstrates competitive or superior performance in mapping, tracking, and rendering compared to existing neural dense SLAM methods.

📄 PDF Abstract BibTeX arXiv:2312.10070

Code (1)

VladimirYugay/Gaussian-SLAM pytorch

Tasks

Simultaneous Localization and Mapping

Similar Papers 제목 키워드 기반

CaRtGS: Computational Alignment for Real-Time Gaussian Splatting SLAM

2024-10-01 · Dapeng Feng, Zhiqiang Chen, Yizhen Yin, Shipeng Zhong 외

Simultaneous Localization and Mapping (SLAM) is pivotal in robotics, with photorealistic scene reconstruction emerging as a key challenge. To address this, we introduce Computational Alignment for Real-Time Gaussian Spla…

3DGSSimultaneous Localization and Mapping

WaterSplat-SLAM: Photorealistic Monocular SLAM in Underwater Environment

2026-04-06 · Kangxu Wang, Shaofeng Zou, Chenxing Jiang, Yixiang Dai 외 arxiv

Underwater monocular SLAM is a challenging problem with applications from autonomous underwater vehicles to marine archaeology. However, existing underwater SLAM methods struggle to produce maps with high-fidelity render…

3D ReconstructionDepth EstimationPose Estimation

MCGS-SLAM: A Multi-Camera SLAM Framework Using Gaussian Splatting for High-Fidelity Mapping

2025-09-17 · Zhihao Cao, Hanyu Wu, Li Wa Tang, Zizhou Luo 외 arxiv

Recent progress in dense SLAM has primarily targeted monocular setups, often at the expense of robustness and geometric coverage. We present MCGS-SLAM, the first purely RGB-based multi-camera SLAM system built on 3D Gaus…

Autonomous Driving

IG-SLAM: Instant Gaussian SLAM

2024-08-02 · F. Aykut Sarikamis, A. Aydin Alatan

3D Gaussian Splatting has recently shown promising results as an alternative scene representation in SLAM systems to neural implicit representations. However, current methods either lack dense depth maps to supervise the…

3D Reconstruction

VIGS-SLAM: Visual Inertial Gaussian Splatting SLAM

2025-12-02 · Zihan Zhu, Wei Zhang, Moyang Li, Norbert Haala 외 arxiv

We present VIGS-SLAM, a visual-inertial 3D Gaussian Splatting SLAM system that achieves robust real-time tracking and high-fidelity reconstruction. Although recent 3DGS-based SLAM methods achieve dense and photorealistic…