GS3LAM: Gaussian Semantic Splatting SLAM

• URL: http://arxiv.org/abs/2603.27781v1
• Date: Sun, 29 Mar 2026 17:25:18 GMT
• Title: GS3LAM: Gaussian Semantic Splatting SLAM
• Abstract summary: We propose GS3LAM, a framework that processes multimodal data to render consistent, dense semantic maps in real-time.<n>A Depth-adaptive Scale Regularization scheme is introduced to resolve misalignments between scale-invariant Gaussians and geometric surfaces.<n>Experiments on benchmark datasets show that GS3LAM achieves increased tracking, superior rendering quality, and enhanced semantic precision.
• Score: 12.867211140172005
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: Recently, the multi-modal fusion of RGB, depth, and semantics has shown great potential in dense Simultaneous Localization and Mapping (SLAM). However, a prerequisite for generating consistent semantic maps is the availability of dense, efficient, and scalable scene representations. Existing semantic SLAM systems based on explicit representations are often limited by resolution and an inability to predict unknown areas. Conversely, implicit representations typically rely on time-consuming ray tracing, failing to meet real-time requirements. Fortunately, 3D Gaussian Splatting (3DGS) has emerged as a promising representation that combines the efficiency of point-based methods with the continuity of geometric structures. To this end, we propose GS3LAM, a Gaussian Semantic Splatting SLAM framework that processes multimodal data to render consistent, dense semantic maps in real-time. GS3LAM models the scene as a Semantic Gaussian Field (SG-Field) and jointly optimizes camera poses and the field via multimodal error constraints. Furthermore, a Depth-adaptive Scale Regularization (DSR) scheme is introduced to resolve misalignments between scale-invariant Gaussians and geometric surfaces. To mitigate catastrophic forgetting, we propose a Random Sampling-based Keyframe Mapping (RSKM) strategy, which demonstrates superior performance over common local covisibility optimization methods. Extensive experiments on benchmark datasets show that GS3LAM achieves increased tracking robustness, superior rendering quality, and enhanced semantic precision compared to state-of-the-art methods. Source code is available at https://github.com/lif314/GS3LAM.

Related papers

• GLAM-SLAM: Real-time Gaussian Large-scale Mapping via Flow Densification and Spatial Decomposition [15.113183931728814]
  We present GLAM-SLAM, a real-time, decoupled Gaussian-splatting SLAM system.<n>We ensure lightweight tracking using a robust, feature-based SLAM.<n>We adopt a structured, sparse anchor grid representation that ensures scalable operation and maintains scene across long-term sequences.<n>We evaluate our system on the challenging, long-sequence KITTI Odometry, Oxford RobotCar, and M Splatalaga datasets.
  arXiv  Detail & Related papers  (2026-07-23T15:22:42Z)
• VBGS-SLAM: Variational Bayesian Gaussian Splatting Simultaneous Localization and Mapping [11.158238000818288]
  3D Gaussian Splatting (3DGS) has shown promising results for 3D scene modeling using mixtures of Gaussians.<n>We propose Variational Bayesian Gaussian Splatting SLAM (VBGS-SLAM), a novel framework that couples the splat map refinement and camera pose tracking in a generative probabilistic form.<n>Our experiments demonstrate superior tracking performance and robustness in long sequence prediction, alongside efficient, high-quality novel view synthesis across diverse synthetic and real-world scenes.
  arXiv  Detail & Related papers  (2026-04-03T03:44:01Z)
• LangGS-SLAM: Real-Time Language-Feature Gaussian Splatting SLAM [2.738569311610586]
  RGB-D SLAM system reconstructs a language-aligned dense feature field while sustaining low-latency tracking and mapping.<n>System achieves superior geometric fidelity compared to geometric-only baselines and comparable semantic fidelity to offline approaches while operating at 15 FPS.
  arXiv  Detail & Related papers  (2026-01-28T05:35:34Z)
• 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)
• IG-SLAM: Instant Gaussian SLAM [6.228980850646457]
  3D Gaussian Splatting has recently shown promising results as an alternative scene representation in SLAM systems. We present IG-SLAM, a dense RGB-only SLAM system that employs robust Dense-SLAM methods for tracking and combines them with Gaussian Splatting. We demonstrate competitive performance with state-of-the-art RGB-only SLAM systems while achieving faster operation speeds.
  arXiv  Detail & Related papers  (2024-08-02T09:07:31Z)
• Splat-SLAM: Globally Optimized RGB-only SLAM with 3D Gaussians [87.48403838439391]
  3D Splatting has emerged as a powerful representation of geometry and appearance for RGB-only dense Simultaneous SLAM. We propose the first RGB-only SLAM system with a dense 3D Gaussian map representation. Our experiments on the Replica, TUM-RGBD, and ScanNet datasets indicate the effectiveness of globally optimized 3D Gaussians.
  arXiv  Detail & Related papers  (2024-05-26T12:26:54Z)
• SAGS: Structure-Aware 3D Gaussian Splatting [53.6730827668389]
  We propose a structure-aware Gaussian Splatting method (SAGS) that implicitly encodes the geometry of the scene. SAGS reflects to state-of-the-art rendering performance and reduced storage requirements on benchmark novel-view synthesis datasets.
  arXiv  Detail & Related papers  (2024-04-29T23:26:30Z)
• latentSplat: Autoencoding Variational Gaussians for Fast Generalizable 3D Reconstruction [48.86083272054711]
  latentSplat is a method to predict semantic Gaussians in a 3D latent space that can be splatted and decoded by a light-weight generative 2D architecture. We show that latentSplat outperforms previous works in reconstruction quality and generalization, while being fast and scalable to high-resolution data.
  arXiv  Detail & Related papers  (2024-03-24T20:48:36Z)
• SplaTAM: Splat, Track & Map 3D Gaussians for Dense RGB-D SLAM [48.190398577764284]
  SplaTAM is an approach to enable high-fidelity reconstruction from a single unposed RGB-D camera. It employs a simple online tracking and mapping system tailored to the underlying Gaussian representation. Experiments show that SplaTAM achieves up to 2x superior performance in camera pose estimation, map construction, and novel-view synthesis over existing methods.
  arXiv  Detail & Related papers  (2023-12-04T18:53:24Z)
• 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)

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.