mlsanityData to 7 Oct 2026

ORB-SLAM3: An Accurate Open-Source Library for Visual, Visual-Inertial and Multi-Map SLAM

arXiv 2007.11898 ↗First posted 23 Jul 2020cs.ROcited by 862

Not on the map. Why?

Abstract (arXiv)

This paper presents ORB-SLAM3, the first system able to perform visual, visual-inertial and multi-map SLAM with monocular, stereo and RGB-D cameras, using pin-hole and fisheye lens models. The first main novelty is a feature-based tightly-integrated visual-inertial SLAM system that fully relies on Maximum-a-Posteriori (MAP) estimation, even during the IMU initialization phase. The result is a system that operates robustly in real-time, in small and large, indoor and outdoor environments, and is 2 to 5 times more accurate than previous approaches. The second main novelty is a multiple map system that relies on a new place recognition method with improved recall. Thanks to it, ORB-SLAM3 is able to survive to long periods of poor visual information: when it gets lost, it starts a new map that will be seamlessly merged with previous maps when revisiting mapped areas. Compared with visual odometry systems that only use information from the last few seconds, ORB-SLAM3 is the first system able to reuse in all the algorithm stages all previous information. This allows to include in bundle adjustment co-visible keyframes, that provide high parallax observations boosting accuracy, even if they are widely separated in time or if they come from a previous mapping session. Our experiments show that, in all sensor configurations, ORB-SLAM3 is as robust as the best systems available in the literature, and significantly more accurate. Notably, our stereo-inertial SLAM achieves an average accuracy of 3.6 cm on the EuRoC drone and 9 mm under quick hand-held motions in the room of TUM-VI dataset, a setting representative of AR/VR scenarios. For the benefit of the community we make public the source code.

Key facts. Cited by 862 papers in the map (data through 7 Oct 2026). First posted on arXiv 23 Jul 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 55; 2022: 92; 2023: 126; 2024: 196; 2025: 182; 2026: 211.

862 papers.

Sort:

By area:

  1. 2023DUSt3R: Geometric 3D Vision Made Easycited by 1,526
  2. 2024Grounding Image Matching in 3D with MASt3Rcited by 960
  3. 2021DROID-SLAM: Deep Visual SLAM for Monocular, Stereo, and RGB-D Camerascited by 673
  4. 2023Gaussian Splatting SLAMcited by 410
  5. 2023SplaTAM: Splat, Track & Map 3D Gaussians for Dense RGB-D SLAMcited by 386
  6. 2024PGSR: Planar-based Gaussian Splatting for Efficient and High-Fidelity Surface Reconstructioncited by 280
  7. 2021NeuralRecon: Real-Time Coherent 3D Reconstruction from Monocular Videocited by 241
  8. 2024MegaSaM: Accurate, Fast, and Robust Structure and Motion from Casual Dynamic Videoscited by 224
  9. 2024MASt3R-SLAM: Real-Time Dense SLAM with 3D Reconstruction Priorscited by 198
  10. 2025Unified Video Action Modelcited by 195
  11. 2022Deep Patch Visual Odometrycited by 186
  12. 2025ViPE: Video Pose Engine for 3D Geometric Perceptioncited by 162
38 more
  1. 2024MASt3R-SfM: a Fully-Integrated Solution for Unconstrained Structure-from-Motioncited by 161
  2. 2022ESLAM: Efficient Dense SLAM System Based on Hybrid Representation of Signed Distance Fieldscited by 158
  3. 2023Optimal Transport Aggregation for Visual Place Recognitioncited by 151
  4. 2022Vox-Fusion: Dense Tracking and Mapping with Voxel-based Neural Implicit Representationcited by 149
  5. 2021Kimera: from SLAM to Spatial Perception with 3D Dynamic Scene Graphscited by 144
  6. 2023Photo-SLAM: Real-time Simultaneous Localization and Photorealistic Mapping for Monocular, Stereo, and RGB-D Camerascited by 139
  7. 2025MUSt3R: Multi-view Network for Stereo 3D Reconstructioncited by 139
  8. 2023GO-SLAM: Global Optimization for Consistent 3D Instant Reconstructioncited by 132
  9. 2025VGGT-SLAM: Dense RGB SLAM Optimized on the SL(4) Manifoldcited by 130
  10. 2024Cameras as Rays: Pose Estimation via Ray Diffusioncited by 129
  11. 2022ZebraPose: Coarse to Fine Surface Encoding for 6DoF Object Pose Estimationcited by 115
  12. 2021TransformerFusion: Monocular RGB Scene Reconstruction using Transformerscited by 107
  13. 2025VGGT-Long: Chunk it, Loop it, Align it -- Pushing VGGT's Limits on Kilometer-scale Long RGB Sequencescited by 107
  14. 2022RelPose: Predicting Probabilistic Relative Rotation for Single Objects in the Wildcited by 102
  15. 2022VideoDex: Learning Dexterity from Internet Videoscited by 101
  16. 2024SLAM3R: Real-Time Dense Scene Reconstruction from Monocular RGB Videoscited by 100
  17. 2022Ego-Body Pose Estimation via Ego-Head Pose Estimationcited by 93
  18. 2024Stereo4D: Learning How Things Move in 3D from Internet Stereo Videoscited by 89
  19. 2023RelPose++: Recovering 6D Poses from Sparse-view Observationscited by 87
  20. 2024SGS-SLAM: Semantic Gaussian Splatting For Neural Dense SLAMcited by 86
  21. 2022Orbeez-SLAM: A Real-time Monocular Visual SLAM with ORB Features and NeRF-realized Mappingcited by 79
  22. 2024How NeRFs and 3D Gaussian Splatting are Reshaping SLAM: a Surveycited by 72
  23. 2024Deep Patch Visual SLAMcited by 68
  24. 2023vMAP: Vectorised Object Mapping for Neural Field SLAMcited by 67
  25. 2024RGBD GS-ICP SLAMcited by 65
  26. 2023Behind the Scenes: Density Fields for Single View Reconstructioncited by 63
  27. 2024FlowMap: High-Quality Camera Poses, Intrinsics, and Depth via Gradient Descentcited by 61
  28. 2024LoopSplat: Loop Closure by Registering 3D Gaussian Splatscited by 59
  29. 2022EndoMapper dataset of complete calibrated endoscopy procedurescited by 53
  30. 2023EgoLocate: Real-time Motion Capture, Localization, and Mapping with Sparse Body-mounted Sensorscited by 48
  31. 2022ClearPose: Large-scale Transparent Object Dataset and Benchmarkcited by 46
  32. 2022VECtor: A Versatile Event-Centric Benchmark for Multi-Sensor SLAMcited by 45
  33. 2025ControlVLA: Few-shot Object-centric Adaptation for Pre-trained Vision-Language-Action Modelscited by 43
  34. 2024FAST-LIVO2: Fast, Direct LiDAR-Inertial-Visual Odometrycited by 40
  35. 2023Incremental 3D Semantic Scene Graph Prediction from RGB Sequencescited by 39
  36. 2023R3D3: Dense 3D Reconstruction of Dynamic Scenes from Multiple Camerascited by 39
  37. 2023FlowCam: Training Generalizable 3D Radiance Fields without Camera Poses via Pixel-Aligned Scene Flowcited by 38
  38. 2025TartanGround: A Large-Scale Dataset for Ground Robot Perception and Navigationcited by 35

50 most cited of 862 All 862 (JSON)