GaussianFlow SLAM: Monocular Gaussian Splatting SLAM Guided by GaussianFlow

• URL: http://arxiv.org/abs/2604.15612v1
• Date: Fri, 17 Apr 2026 01:34:46 GMT
• Title: GaussianFlow SLAM: Monocular Gaussian Splatting SLAM Guided by GaussianFlow
• Abstract summary: We propose a monocular 3DGS-SLAM that uses optical flow as a geometry-aware cue to guide the optimization of both the scene structure and camera poses.<n>Our method achieves superior rendering quality and tracking accuracy compared with state-of-the-art algorithms.
• Score: 7.598885266145037
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Gaussian splatting has recently gained traction as a compelling map representation for SLAM systems, enabling dense and photo-realistic scene modeling. However, its application to monocular SLAM remains challenging due to the lack of reliable geometric cues from monocular input. Without geometric supervision, mapping or tracking could fall in local-minima, resulting in structural degeneracies and inaccuracies. To address this challenge, we propose GaussianFlow SLAM, a monocular 3DGS-SLAM that leverages optical flow as a geometry-aware cue to guide the optimization of both the scene structure and camera poses. By encouraging the projected motion of Gaussians, termed GaussianFlow, to align with the optical flow, our method introduces consistent structural cues to regularize both map reconstruction and pose estimation. Furthermore, we introduce normalized error-based densification and pruning modules to refine inactive and unstable Gaussians, thereby contributing to improved map quality and pose accuracy. Experiments conducted on public datasets demonstrate that our method achieves superior rendering quality and tracking accuracy compared with state-of-the-art algorithms. The source code is available at: https://github.com/url-kaist/gaussianflow-slam.

Related papers

• Flow4DGS-SLAM: Optical Flow-Guided 4D Gaussian Splatting SLAM [55.56111618153049]
  We propose an efficient framework for dynamic 3DGS SLAM guided by optical flow.<n>We boost the training speed of dynamic 3DGS by explicitly modeling their temporal centers.<n>The empirical results demonstrate our state-of-the-art performance in tracking, dynamic reconstruction, and training efficiency.
  arXiv  Detail & Related papers  (2026-04-24T08:13:01Z)
• VIGS-SLAM: Visual Inertial Gaussian Splatting SLAM [75.55522219717137]
  We present VIGS-SLAM, a visual-inertial 3D Gaussian Splatting SLAM system.<n>It achieves robust real-time tracking and high-fidelity reconstruction.<n>Our method tightly couples visual and inertial cues within a unified optimization framework.
  arXiv  Detail & Related papers  (2025-12-02T00:19:13Z)
• Pseudo Depth Meets Gaussian: A Feed-forward RGB SLAM Baseline [64.42938561167402]
  We propose an online 3D reconstruction method using 3D Gaussian-based SLAM, combined with a feed-forward recurrent prediction module.<n>This approach replaces slow test-time optimization with fast network inference, significantly improving tracking speed.<n>Our method achieves performance on par with the state-of-the-art SplaTAM, while reducing tracking time by more than 90%.
  arXiv  Detail & Related papers  (2025-08-06T16:16:58Z)
• GauS-SLAM: Dense RGB-D SLAM with Gaussian Surfels [5.726938101368279]
  GauS-SLAM is a dense RGB-D SLAM system that leverages 2D Gaussian surfels to achieve robust tracking and high-fidelity mapping.<n>GauS-SLAM outperforms comparable methods, delivering superior tracking precision and rendering fidelity.
  arXiv  Detail & Related papers  (2025-05-03T22:02:20Z)
• RP-SLAM: Real-time Photorealistic SLAM with Efficient 3D Gaussian Splatting [22.76955981251234]
  RP-SLAM is a 3D Gaussian splatting-based vision SLAM method for monocular and RGB-D cameras.<n>It achieves state-of-the-art map rendering accuracy while ensuring real-time performance and model compactness.
  arXiv  Detail & Related papers  (2024-12-13T05:27:35Z)
• MGS-SLAM: Monocular Sparse Tracking and Gaussian Mapping with Depth Smooth Regularization [29.713650915551632]
  This letter introduces a novel framework for dense Visual Simultaneous Localization and Mapping based on Gaussian Splatting. We jointly optimize sparse visual odometry tracking and 3D Gaussian Splatting scene representation for the first time. The accuracy of our pose estimation surpasses existing methods and state-of-the-art.
  arXiv  Detail & Related papers  (2024-05-10T04:42:21Z)
• SLAIM: Robust Dense Neural SLAM for Online Tracking and Mapping [15.63276368052395]
  We propose a novel coarse-to-fine tracking model tailored for Neural Radiance Field SLAM (NeRF-SLAM) Existing NeRF-SLAM systems consistently exhibit inferior tracking performance compared to traditional SLAM algorithms. We implement both local and global bundle-adjustment to produce a robust (coarse-to-fine) and accurate (KL regularizer) SLAM solution.
  arXiv  Detail & Related papers  (2024-04-17T14:23:28Z)
• CG-SLAM: Efficient Dense RGB-D SLAM in a Consistent Uncertainty-aware 3D Gaussian Field [46.8198987091734]
  This paper presents an efficient dense RGB-D SLAM system, i.e., CG-SLAM, based on a novel uncertainty-aware 3D Gaussian field. Experiments on various datasets demonstrate that CG-SLAM achieves superior tracking and mapping performance with a notable tracking speed of up to 15 Hz.
  arXiv  Detail & Related papers  (2024-03-24T11:19:59Z)
• GS-SLAM: Dense Visual SLAM with 3D Gaussian Splatting [51.96353586773191]
  We introduce textbfGS-SLAM that first utilizes 3D Gaussian representation in the Simultaneous Localization and Mapping system. Our method utilizes a real-time differentiable splatting rendering pipeline that offers significant speedup to map optimization and RGB-D rendering. Our method achieves competitive performance compared with existing state-of-the-art real-time methods on the Replica, TUM-RGBD datasets.
  arXiv  Detail & Related papers  (2023-11-20T12:08:23Z)
• GAFlow: Incorporating Gaussian Attention into Optical Flow [62.646389181507764]
  We push Gaussian Attention (GA) into the optical flow models to accentuate local properties during representation learning. We introduce a novel Gaussian-Constrained Layer (GCL) which can be easily plugged into existing Transformer blocks. For reliable motion analysis, we provide a new Gaussian-Guided Attention Module (GGAM)
  arXiv  Detail & Related papers  (2023-09-28T07:46:01Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.