SplaTAM: Splat, Track & Map 3D Gaussians for Dense RGB-D SLAM
Not on the map. Why?
Abstract (arXiv)
Dense simultaneous localization and mapping (SLAM) is crucial for robotics and augmented reality applications. However, current methods are often hampered by the non-volumetric or implicit way they represent a scene. This work introduces SplaTAM, an approach that, for the first time, leverages explicit volumetric representations, i.e., 3D Gaussians, to enable high-fidelity reconstruction from a single unposed RGB-D camera, surpassing the capabilities of existing methods. SplaTAM employs a simple online tracking and mapping system tailored to the underlying Gaussian representation. It utilizes a silhouette mask to elegantly capture the presence of scene density. This combination enables several benefits over prior representations, including fast rendering and dense optimization, quickly determining if areas have been previously mapped, and structured map expansion by adding more Gaussians. Extensive experiments show that SplaTAM achieves up to 2x superior performance in camera pose estimation, map construction, and novel-view synthesis over existing methods, paving the way for more immersive high-fidelity SLAM applications.
Key facts. Cited by 386 papers in the map (data through 7 Oct 2026). Builds on 41 of its 57 references that are in the map. First posted on arXiv 4 Dec 2023.
Builds on
41 of 57 references.
References · 41
- 20233D Gaussian Splatting for Real-Time Radiance Field Renderingcited by 6,141
- 2017ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenescited by 3,088
- 20234D Gaussian Splatting for Real-Time Dynamic Scene Renderingcited by 1,144
- 2019The Replica Dataset: A Digital Replica of Indoor Spacescited by 885
- 2020ORB-SLAM3: An Accurate Open-Source Library for Visual, Visual-Inertial and Multi-Map SLAMcited by 862
- 2016ORB-SLAM2: an Open-Source SLAM System for Monocular, Stereo and RGB-D Camerascited by 801
- 2023Deformable 3D Gaussians for High-Fidelity Monocular Dynamic Scene Reconstructioncited by 753
- 2023ScanNet++: A High-Fidelity Dataset of 3D Indoor Scenescited by 747
- 2023Dynamic 3D Gaussians: Tracking by Persistent Dynamic View Synthesiscited by 731
- 2021DROID-SLAM: Deep Visual SLAM for Monocular, Stereo, and RGB-D Camerascited by 673
- 2021NICE-SLAM: Neural Implicit Scalable Encoding for SLAMcited by 586
- 2022Point-NeRF: Point-based Neural Radiance Fieldscited by 503
29 more
- 2021iMAP: Implicit Mapping and Positioning in Real-Timecited by 476
- 2023Real-time Photorealistic Dynamic Scene Representation and Rendering with 4D Gaussian Splattingcited by 470
- 2016Past, Present, and Future of Simultaneous Localization And Mapping: Towards the Robust-Perception Agecited by 405
- 2019Differentiable Surface Splatting for Point-based Geometry Processingcited by 238
- 2022NeRF-SLAM: Real-Time Dense Monocular SLAM with Neural Radiance Fieldscited by 188
- 2023Co-SLAM: Joint Coordinate and Sparse Parametric Encodings for Neural Real-Time SLAMcited by 183
- 2023NICER-SLAM: Neural Implicit Scene Encoding for RGB SLAMcited by 162
- 2023Point-SLAM: Dense Neural Point Cloud-based SLAMcited by 160
- 2022ESLAM: Efficient Dense SLAM System Based on Hybrid Representation of Signed Distance Fieldscited by 158
- 2017CNN-SLAM: Real-time dense monocular SLAM with learned depth predictioncited by 152
- 2018CodeSLAM - Learning a Compact, Optimisable Representation for Dense Visual SLAMcited by 151
- 2022Vox-Fusion: Dense Tracking and Mapping with Voxel-based Neural Implicit Representationcited by 149
- 2016Voxblox: Incremental 3D Euclidean Signed Distance Fields for On-Board MAV Planningcited by 148
- 2016BundleFusion: Real-time Globally Consistent 3D Reconstruction using On-the-fly Surface Re-integrationcited by 116
- 2022iSDF: Real-Time Neural Signed Distance Fields for Robot Perceptioncited by 107
- 2022LaMAR: Benchmarking Localization and Mapping for Augmented Realitycited by 98
- 2018DeepTAM: Deep Tracking and Mappingcited by 87
- 2023vMAP: Vectorised Object Mapping for Neural Field SLAMcited by 67
- 2022Approximate Differentiable Rendering with Algebraic Surfacescited by 44
- 2023Dense RGB SLAM with Neural Implicit Mapscited by 42
- 2019SceneCode: Monocular Dense Semantic Reconstruction using Learned Encoded Scene Representationscited by 37
- 2023HI-SLAM: Monocular Real-time Dense Mapping with Hybrid Implicit Fieldscited by 31
- 2023Flexible Techniques for Differentiable Rendering with 3D Gaussianscited by 28
- 2022VoGE: A Differentiable Volume Renderer using Gaussian Ellipsoids for Analysis-by-Synthesiscited by 22
- 2022iDF-SLAM: End-to-End RGB-D SLAM with Neural Implicit Mapping and Deep Feature Trackingcited by 22
- 2023UncLe-SLAM: Uncertainty Learning for Dense Neural SLAMcited by 19
- 2023RO-MAP: Real-Time Multi-Object Mapping with Neural Radiance Fieldscited by 9
- 2023Probabilistic Point Cloud Modeling via Self-Organizing Gaussian Mixture Modelscited by 7
- 2023Incremental Multimodal Surface Mapping via Self-Organizing Gaussian Mixture Modelscited by 5
Built on by
Citing papers per year: 2023: 3; 2024: 132; 2025: 143; 2026: 108.
386 papers.
Sort:
By area:
- 2025MapAnything: Universal Feed-Forward Metric 3D Reconstructioncited by 295
- 20243D Reconstruction with Spatial Memorycited by 269
- 2025AnySplat: Feed-forward 3D Gaussian Splatting from Unconstrained Viewscited by 234
- 2024Octree-GS: Towards Consistent Real-time Rendering with LOD-Structured 3D Gaussianscited by 225
- 2024A Survey on 3D Gaussian Splattingcited by 221
- 2024MASt3R-SLAM: Real-Time Dense SLAM with 3D Reconstruction Priorscited by 198
- 2025FLARE: Feed-forward Geometry, Appearance and Camera Estimation from Uncalibrated Sparse Viewscited by 176
- 2023Gaussian-SLAM: Photo-realistic Dense SLAM with Gaussian Splattingcited by 152
- 2024OpenGaussian: Towards Point-Level 3D Gaussian-based Open Vocabulary Understandingcited by 141
- 2024Recent Advances in 3D Gaussian Splattingcited by 130
- 2024Revising Densification in Gaussian Splattingcited by 127
- 20243D Gaussian as a New Era: A Surveycited by 102
38 more
- 2024SLAM3R: Real-Time Dense Scene Reconstruction from Monocular RGB Videoscited by 100
- 2023Toward General-Purpose Robots via Foundation Models: A Survey and Meta-Analysiscited by 99
- 2024GaussianFlow: Splatting Gaussian Dynamics for 4D Content Creationcited by 99
- 2024GaussianImage: 1000 FPS Image Representation and Compression by 2D Gaussian Splattingcited by 97
- 2024FMGS: Foundation Model Embedded 3D Gaussian Splatting for Holistic 3D Scene Understandingcited by 86
- 2024SGS-SLAM: Semantic Gaussian Splatting For Neural Dense SLAMcited by 86
- 2024FreeSplat: Generalizable 3D Gaussian Splatting Towards Free-View Synthesis of Indoor Scenescited by 86
- 2024FlashGS: Efficient 3D Gaussian Splatting for Large-scale and High-resolution Renderingcited by 85
- 2024GSDF: 3DGS Meets SDF for Improved Rendering and Reconstructioncited by 81
- 20243D Gaussian Splatting: Survey, Technologies, Challenges, and Opportunitiescited by 77
- 2024How NeRFs and 3D Gaussian Splatting are Reshaping SLAM: a Surveycited by 72
- 2024Deep Patch Visual SLAMcited by 68
- 2024RGBD GS-ICP SLAMcited by 65
- 2024Splat-SLAM: Globally Optimized RGB-only SLAM with 3D Gaussianscited by 64
- 2024MotionGS: Exploring Explicit Motion Guidance for Deformable 3D Gaussian Splattingcited by 62
- 2024CG-SLAM: Efficient Dense RGB-D SLAM in a Consistent Uncertainty-aware 3D Gaussian Fieldcited by 61
- 2024FlowMap: High-Quality Camera Poses, Intrinsics, and Depth via Gradient Descentcited by 61
- 2024PF3plat: Pose-Free Feed-Forward 3D Gaussian Splattingcited by 60
- 2024LoopSplat: Loop Closure by Registering 3D Gaussian Splatscited by 59
- 2024Radiative Gaussian Splatting for Efficient X-ray Novel View Synthesiscited by 56
- 2024GeoGaussian: Geometry-aware Gaussian Splatting for Scene Renderingcited by 52
- 2024DOGS: Distributed-Oriented Gaussian Splatting for Large-Scale 3D Reconstruction Via Gaussian Consensuscited by 51
- 2024GaussNav: Gaussian Splatting for Visual Navigationcited by 49
- 2025WildGS-SLAM: Monocular Gaussian Splatting SLAM in Dynamic Environmentscited by 48
- 2024EgoLifter: Open-world 3D Segmentation for Egocentric Perceptioncited by 46
- 2024SemGauss-SLAM: Dense Semantic Gaussian Splatting SLAMcited by 41
- 2024Gaussian Splatting: 3D Reconstruction and Novel View Synthesis, a Reviewcited by 40
- 2024SelfSplat: Pose-Free and 3D Prior-Free Generalizable 3D Gaussian Splattingcited by 40
- 2024WaterSplatting: Fast Underwater 3D Scene Reconstruction Using Gaussian Splattingcited by 39
- 2025GWM: Towards Scalable Gaussian World Models for Robotic Manipulationcited by 37
- 2024GlORIE-SLAM: Globally Optimized RGB-only Implicit Encoding Point Cloud SLAMcited by 36
- 2024HDR-GS: Efficient High Dynamic Range Novel View Synthesis at 1000x Speed via Gaussian Splattingcited by 35
- 2025TartanGround: A Large-Scale Dataset for Ground Robot Perception and Navigationcited by 35
- 2025On-the-fly Reconstruction for Large-Scale Novel View Synthesis from Unposed Imagescited by 35
- 2024ActiveSplat: High-Fidelity Scene Reconstruction through Active Gaussian Splattingcited by 32
- 2024Baking Gaussian Splatting into Diffusion Denoiser for Fast and Scalable Single-stage Image-to-3D Generation and Reconstructioncited by 32
- 2025Any4D: Unified Feed-Forward Metric 4D Reconstructioncited by 32
- 2024Gaussian Splatting on the Move: Blur and Rolling Shutter Compensation for Natural Camera Motioncited by 29
50 most cited of 386 All 386 (JSON)
- 2026CLoSeR: Closing the Loop for Long-Context Streaming Reconstruction1 Oct 2026
- 2026LiTe-GS: Oracle-Efficient Next Best View Selection for 3D Gaussian Splatting24 Sep 2026
- 2026Dual Covariance Gaussian Splatting SLAM: Decoupling Rendering and Registration for Robust Real-Time Tracking22 Sep 2026
- 2026CODA: Depth-Aligned Scene Completion and Object Decomposition from a Single RGB-D Image22 Sep 2026
- 2026Adaptive World Memory 3D Foundation Model for Scalable 3D Mapping, Localization, and Rendering18 Sep 2026
- 2026VoxelTTO: Voxel-Aligned Feed-Forward 3D Gaussian Splatting with Test-Time Optimization18 Sep 2026
- 2026Cube-Splat: High-Fidelity 360deg Gaussian Splatting SLAM via Cubemap Factorization and Adjoint-Consistent Optimization18 Sep 2026
- 2026RawSLAM: Online HDR Gaussian SLAM from Linear Radiance17 Sep 2026
- 2026EliGSiR: Continual RGB-D Mapping with Gaussian Splatting under Bounded Compute17 Sep 2026
- 2026VGGT-GS SLAM: Uncalibrated Monocular Gaussian Splatting SLAM with Feed-Forward Priors17 Sep 2026
- 2026PanoGS-SLAM: Panoramic 3D Gaussian Splatting SLAM15 Sep 2026
- 2026SCOUT-SLAM: Structurally-Coupled Dual Uncertainty-Aware 3DGS SLAM in the Wild13 Sep 2026
38 more
- 2026LightSplat: Real-Time High-Fidelity 3D Gaussian SLAM with Loop Closure7 Sep 2026
- 2026From Splats to Silicon: Rethinking Computational Efficiency of 3DGS5 Sep 2026
- 2026VI3: Grounding Pretrained 3D Foundation Models with Inertial Cues3 Sep 2026
- 2026DSG: Dynamic 3D Scene Graph Construction for Embodied Agents in Changing Indoor Environments1 Sep 2026
- 2026Failure or Drift? Evaluating Monocular SLAM under Synthetic and Real-World Corruptions31 Aug 2026
- 2026RoSe-SLAM: Robust Semantic-Aware Gaussian Splatting SLAM from Dynamic Monocular Videos29 Aug 2026
- 2026NemoSplat: Feed-Forward 4D Gaussian Splatting for Media-Aware Underwater Reconstruction24 Aug 2026
- 2026MotionGS-SLAM: Event-Modulated Gaussian Splatting for Motion-Blur Robust SLAM15 Aug 2026
- 2026DeGS: A Scalable 3DGS Architecture via Decoupled Workload Parsing and Reorganization3 Aug 2026
- 2026CHOW-SLAM: Compact Hybrid Representation with Complementary Overlap Window Optimization for RGB-D SLAM3 Aug 2026
- 2026DynActiveGS: Active Gaussian Splatting for Dynamic Scene Reconstruction2 Aug 2026
- 2026Stipple: Real-Time Incremental Gaussian Splatting with Visual-Inertial Tracking2 Aug 2026
- 2026MonoVoc: Decoupling Geometry and Semantics for Lightweight Monocular Open-Vocabulary 3D Gaussians30 Jul 2026
- 2026CORF-GS: Real-Time Wireless Radiance Field Reconstruction via Coupled Optical-RF Gaussian Splatting28 Jul 2026
- 2026NSL-SLAM: High-Fidelity Neural Structured-Light Depth for Practical SLAM and Reconstruction27 Jul 2026
- 2026GLAM-SLAM: Real-time Gaussian Large-scale Mapping via Flow Densification and Spatial Decomposition23 Jul 2026
- 2026Splat-based 3D Scene Reconstruction with Extreme Motion-blur18 Jul 2026
- 2026Rendering 3D Gaussians on a Graph Processor17 Jul 2026
- 2026ImprovedVBGS: Real-time Continual Variational Bayes Gaussian Splatting17 Jul 2026
- 2026MAGiSt3R: Multi-Agent Feed-forward 3D Reconstruction from Monocular RGB Videos16 Jul 2026
- 2026VistaVLA: Geometry- and Semantic-Aware 3D Gaussian-Grounded VLA for Robotic Manipulation14 Jul 2026
- 2026MAC-Splat: Multi-Attribute Consistency for High-Fidelity Sparse-View Reconstruction12 Jul 2026
- 2026SplatCtrl: Perception-Action Coupling via Gaussian Scene Representations and Reactive Robot Control9 Jul 2026
- 2026AdaptiveSplat:Texture Aware Controllable 3D Gaussian Allocation for Feed-Forward Reconstruction5 Jul 2026
- 2026Real-Time LiDAR Gaussian Splatting SLAM5 Jul 2026
- 2026Diversity-aware View Partitioning for Scalable VGGT2 Jul 2026
- 2026GaussLite: Online Task-Conditioned 3D Gaussian Splatting for Real-Time Robotic Mapping29 Jun 2026
- 2026Open-Vocabulary and Referring Segmentation for 3D Gaussians Using 2D Detectors29 Jun 2026
- 2026Robust and Efficient Monocular 3D Gaussian SLAM for Kilometer-Scale Outdoor Scenes29 Jun 2026
- 2026Argus: Metric Panoramic 3D Reconstruction for Indoor Scenes29 Jun 2026
- 2026VCS-SLAM: Geometry-Validated Semantic Evidence Fusion for 3D Gaussian SLAM28 Jun 2026
- 2026RAGA: Real Time Ray Traced Gaussian Shadow Casting for 3DGS Avatar-Scene Interaction28 Jun 2026
- 2026MoPe: Motion Permanence for Robust Monocular Gaussian Mapping in Dynamic Environments28 Jun 2026
- 2026Non-line-of-sight imaging with arbitrary relay surface geometries via 3D Gaussian Transient Rendering19 Jun 2026
- 2026Spectral GS-SLAM: Observability-Aware, Degeneracy-Robust Tracking for Real-Time 3D Gaussian Splatting SLAM19 Jun 2026
- 2026MMD-SLAM: Structure-Enhanced Multi-Meta Gaussian Distribution-Guided Visual SLAM18 Jun 2026
- 2026VG2GT: Voxel-Gaussian Splatting Visual Geometry Grounded Transformer1 Jun 2026
- 2026Triangle Splatting SLAM29 May 2026
50 newest of 386 All 386 (JSON)
- 2024Baking Gaussian Splatting into Diffusion Denoiser for Fast and Scalable Single-stage Image-to-3D Generation and Reconstructioncited by 32
- 2024LM-Gaussian: Boost Sparse-view 3D Gaussian Splatting with Large Model Priorscited by 25
- 2025GSFix3D: Diffusion-Guided Repair of Novel Views in Gaussian Splattingcited by 17
- 2024SRIF: Semantic Shape Registration Empowered by Diffusion-based Image Morphing and Flow Estimationcited by 12
- 2025UnPose: Uncertainty-Guided Diffusion Priors for Zero-Shot Pose Estimationcited by 2
- 2026FreeFix: Boosting 3D Gaussian Splatting via Fine-Tuning-Free Diffusion Modelscited by 2
- 2026AHOY! Animatable Humans under Occlusion from YouTube Videos with Gaussian Splatting and Video Diffusion Priorscited by 2
- 2025SplatSearch: Instance Image Goal Navigation for Mobile Robots using 3D Gaussian Splatting and Diffusion Modelscited by 1
- 2026AHOY! Animatable Humans under Occlusion from YouTube Videos with Gaussian Splatting and Video Diffusion Priors18 Mar 2026
- 2026FreeFix: Boosting 3D Gaussian Splatting via Fine-Tuning-Free Diffusion Models28 Jan 2026
- 2025SplatSearch: Instance Image Goal Navigation for Mobile Robots using 3D Gaussian Splatting and Diffusion Models17 Nov 2025
- 2025UnPose: Uncertainty-Guided Diffusion Priors for Zero-Shot Pose Estimation21 Aug 2025
- 2025GSFix3D: Diffusion-Guided Repair of Novel Views in Gaussian Splatting20 Aug 2025
- 2024Baking Gaussian Splatting into Diffusion Denoiser for Fast and Scalable Single-stage Image-to-3D Generation and Reconstruction21 Nov 2024
- 2024SRIF: Semantic Shape Registration Empowered by Diffusion-based Image Morphing and Flow Estimation18 Sep 2024
- 2024LM-Gaussian: Boost Sparse-view 3D Gaussian Splatting with Large Model Priors5 Sep 2024
- 2025GWM: Towards Scalable Gaussian World Models for Robotic Manipulationcited by 37
- 2024VDG: Vision-Only Dynamic Gaussian for Driving Simulationcited by 16
- 2026From Perception to Action: Spatial AI Agents and World Modelscited by 0
- 2026F3DGS: Federated 3D Gaussian Splatting for Decentralized Multi-Agent World Modelingcited by 0
- 2026F3DGS: Federated 3D Gaussian Splatting for Decentralized Multi-Agent World Modeling2 Apr 2026
- 2026From Perception to Action: Spatial AI Agents and World Models2 Feb 2026
- 2025GWM: Towards Scalable Gaussian World Models for Robotic Manipulation25 Aug 2025
- 2024VDG: Vision-Only Dynamic Gaussian for Driving Simulation26 Jun 2024
- 2025MapAnything: Universal Feed-Forward Metric 3D Reconstructioncited by 295
- 20243D Reconstruction with Spatial Memorycited by 269
- 2025AnySplat: Feed-forward 3D Gaussian Splatting from Unconstrained Viewscited by 234
- 2024Octree-GS: Towards Consistent Real-time Rendering with LOD-Structured 3D Gaussianscited by 225
- 2024A Survey on 3D Gaussian Splattingcited by 221
- 2024MASt3R-SLAM: Real-Time Dense SLAM with 3D Reconstruction Priorscited by 198
- 2025FLARE: Feed-forward Geometry, Appearance and Camera Estimation from Uncalibrated Sparse Viewscited by 176
- 2023Gaussian-SLAM: Photo-realistic Dense SLAM with Gaussian Splattingcited by 152
- 2024OpenGaussian: Towards Point-Level 3D Gaussian-based Open Vocabulary Understandingcited by 141
- 2024Recent Advances in 3D Gaussian Splattingcited by 130
- 2024Revising Densification in Gaussian Splattingcited by 127
- 20243D Gaussian as a New Era: A Surveycited by 102
12 most cited of 368 All 368 (JSON)
- 2026CLoSeR: Closing the Loop for Long-Context Streaming Reconstruction1 Oct 2026
- 2026LiTe-GS: Oracle-Efficient Next Best View Selection for 3D Gaussian Splatting24 Sep 2026
- 2026Dual Covariance Gaussian Splatting SLAM: Decoupling Rendering and Registration for Robust Real-Time Tracking22 Sep 2026
- 2026CODA: Depth-Aligned Scene Completion and Object Decomposition from a Single RGB-D Image22 Sep 2026
- 2026VoxelTTO: Voxel-Aligned Feed-Forward 3D Gaussian Splatting with Test-Time Optimization18 Sep 2026
- 2026Cube-Splat: High-Fidelity 360deg Gaussian Splatting SLAM via Cubemap Factorization and Adjoint-Consistent Optimization18 Sep 2026
- 2026RawSLAM: Online HDR Gaussian SLAM from Linear Radiance17 Sep 2026
- 2026EliGSiR: Continual RGB-D Mapping with Gaussian Splatting under Bounded Compute17 Sep 2026
- 2026VGGT-GS SLAM: Uncalibrated Monocular Gaussian Splatting SLAM with Feed-Forward Priors17 Sep 2026
- 2026PanoGS-SLAM: Panoramic 3D Gaussian Splatting SLAM15 Sep 2026
- 2026SCOUT-SLAM: Structurally-Coupled Dual Uncertainty-Aware 3DGS SLAM in the Wild13 Sep 2026
- 2026LightSplat: Real-Time High-Fidelity 3D Gaussian SLAM with Loop Closure7 Sep 2026
12 newest of 368 All 368 (JSON)