ORB-SLAM: A Versatile and Accurate Monocular SLAM System
Open accessThe DOI matches its Crossref record; 46 of the 46 references it cites were found in a registry or an index.
Abstract
This paper presents ORB-SLAM, a feature-based monocular simultaneous localization and mapping (SLAM) system that operates in real time, in small and large indoor and outdoor environments. The system is robust to severe motion clutter, allows wide baseline loop closing and relocalization, and includes full automatic initialization. Building on excellent algorithms of recent years, we designed from scratch a novel system that uses the same features for all SLAM tasks: tracking, mapping, relocalization, and loop closing. A survival of the fittest strategy that selects the points and keyframes of the reconstruction leads to excellent robustness and generates a compact and trackable map that only grows if the scene content changes, allowing lifelong operation. We present an exhaustive evaluation in 27 sequences from the most popular datasets. ORB-SLAM achieves unprecedented performance with respect to other state-of-the-art monocular SLAM approaches. For the benefit of the community, we make the source code public.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“Most SLAM methods represent the scene as a set of sparse 3D landmarks corresponding to discriminative features in the environment (e.g., lines, corners) [179]”
From Past, Present, and Future of Simultaneous Localization and Mapping: Toward the Robust-Perception Age (2016) · cites this paper as [179]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Distinctive Image Features from Scale-Invariant Keypoints
Lowe, D. G. (2004) · International Journal of Computer Vision · doi:10.1023/b:visi.0000029664.99615.94 · Cited by 55,589 · cited 3×
“This reduced in more than one order of magnitude the time needed for feature extraction, compared with SURF [18] and SIFT [19] features that were used in bags of words approaches so far.”
MethodMultiple View Geometry in Computer Vision
Hartley, R., & Zisserman, A. (2004) · doi:10.1017/cbo9780511811685 · Cited by 21,070
SURF: Speeded Up Robust Features
Bay, H., Tuytelaars, T., & Van Gool, L. (2006) · Lecture Notes in Computer Science · doi:10.1007/11744023_32 · Cited by 14,955
ORB: An efficient alternative to SIFT or SURF
Rublee, E., Rabaud, V., Konolige, K., & Bradski, G. (2011) · 2011 International Conference on Computer Vision · doi:10.1109/iccv.2011.6126544 · Cited by 11,037 · cited 3×
“We chose ORB [9], which are oriented multiscale FAST corners with a 256-bit descriptor associated.”
BackgroundMethodVision meets robotics: The KITTI dataset
Geiger, A., Lenz, P., Stiller, C., & Urtasun, R. (2013) · The International Journal of Robotics Research · doi:10.1177/0278364913491297 · Cited by 9,913 · cited 3×
“The odometry benchmark from the KITTI dataset [40] contains 11 sequences from a car driven around a residential area with accurate ground truth from GPS and a Velodyne laser scanner.”
MethodMachine Learning for High-Speed Corner Detection
Rosten, E., & Drummond, T. (2006) · Lecture Notes in Computer Science · doi:10.1007/11744023_34 · Cited by 4,555 · cited 1×
“DBoW2 [5] used for the first time bags of binary words obtained from BRIEF descriptors [16] along with the very efficient FAST feature detector [17].”
MethodParallel Tracking and Mapping for Small AR Workspaces
Klein, G., & Murray, D. (2007) · 2007 6th IEEE and ACM International Symposium on Mixed and Augmented Reality · doi:10.1109/ismar.2007.4538852 · Cited by 4,346 · cited 7×
“The most representative keyframe-based SLAM system is probably PTAM by Klein and Murray [4].”
MethodInfluentialClosed-form solution of absolute orientation using unit quaternions
Horn, B. K. P. (1987) · Journal of the Optical Society of America A · doi:10.1364/josaa.4.000629 · Cited by 4,116
Bundle Adjustment — A Modern Synthesis
Triggs, B., McLauchlan, P. F., Hartley, R. I., & Fitzgibbon, A. W. (2000) · Lecture Notes in Computer Science · doi:10.1007/3-540-44480-7_21 · Cited by 3,988 · cited 3×
“BUNDLE adjustment (BA) is known to provide accurate estimates of camera localizations as well as a sparse geometrical reconstruction [1], [2], given that a strong network of matches and good initial guesses are provided.”
BackgroundInfluentialA benchmark for the evaluation of RGB-D SLAM systems
Sturm, J., Engelhard, N., Endres, F., Burgard, W., & Cremers, D. (2012) · 2012 IEEE/RSJ International Conference on Intelligent Robots and Systems · doi:10.1109/iros.2012.6385773 · Cited by 3,976 · cited 6×
“Reconstruction and graphs in the sequence fr3 long off ice household from the TUM RGB-D Benchmark [38].”
BackgroundMethodInfluential
Cited by
Items 501–600 of 1,007
Aerial orthoimage generation for UAV remote sensing: Review
Zhang, J., Xu, S., Zhao, Y., Sun, J., Xu, S., & Zhang, X. (2022) · Information Fusion · doi:10.1016/j.inffus.2022.08.007 · Cited by 88
BIM-based indoor mobile robot initialization for construction automation using object detection
Zhao, X., & Cheah, C. C. (2022) · Automation in Construction · doi:10.1016/j.autcon.2022.104647 · Cited by 76
Real-Time Motion Tracking for Mobile Augmented/Virtual Reality Using Adaptive Visual-Inertial Fusion
Fang, W., Zheng, L., Deng, H., & Zhang, H. (2017) · Sensors · doi:10.3390/s17051037 · Cited by 87
“The open-source ORB-SLAM [17] provides a valuable visual-SLAM framework for our work.”
BackgroundMethodInfluentialOngoing Evolution of Visual SLAM from Geometry to Deep Learning: Challenges and Opportunities
Li, R., Wang, S., & Gu, D. (2018) · Cognitive Computation · doi:10.1007/s12559-018-9591-8 · Cited by 85
Bird's eye view: Cooperative exploration by UGV and UAV
Hood, S., Benson, K., Hamod, P., Madison, D., O’Kane, J. M., & Rekleitis, I. M. (2017) · International Conference on Unmanned Aircraft Systems (ICUAS) · doi:10.1109/icuas.2017.7991513 · Cited by 85
“Another later monocular SLAM package, ORBSLAM [4], improves upon the work by Klein and Murray.”
BackgroundMethodInfluentialJiang, G., Yin, L., Jin, S., Tian, C., Ma, X., & Ou, Y. (2019) · Applied Sciences · doi:10.3390/app9102105 · Cited by 85
“8 Orb-SLAM Localization [9] Feature map with camera 88% 5.”
BackgroundMethodInfluentialRobust Visual Localization in Dynamic Environments Based on Sparse Motion Removal
Cheng, J., Wang, C., & Meng, M. Q. ‐. (2019) · IEEE Transactions on Automation Science and Engineering · doi:10.1109/tase.2019.2940543 · Cited by 76
“In a typical way, a visual simultaneous localization and mapping (SLAM) system [8] or visual odometry (VO) [9] sys-tem is adopted as the basic localization scheme.”
MethodMemon, A. R., Wang, H., & Hussain, A. (2020) · Robotics and Autonomous Systems · doi:10.1016/j.robot.2020.103470 · Cited by 82
A survey on edge computing for wearable technology
Jin, X., Li, L., Dang, F., Chen, X., & Liu, Y. (2021) · Digital Signal Processing · doi:10.1016/j.dsp.2021.103146 · Cited by 89
“, Samsung Galaxy S10 and Google Pixel 2) cannot execute computing-intensive ORBSLAM [65] at 15 frames per second (FPS) alone, not to mention resource-limited wearable devices.”
Learnable Motion Coherence for Correspondence Pruning
Liu, Y., Liu, L., Lin, C. C., Dong, Z., & Wang, W. (2021) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr46437.2021.00325 · Cited by 92
“Estimating correspondences between two images is a fundamental problem in computer vision tasks such as Structure-from-Motion (SfM) [19], visual localization [45], image stitching [10] and visual SLAM [32].”
BackgroundDynaNet: Neural Kalman Dynamical Model for Motion Estimation and Prediction
Chen, C., Lu, C. X., Wang, B., Trigoni, N., & Markham, A. (2021) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2021.3112460 · Cited by 85
Seetohul, J., Shafiee, M., & Sirlantzis, K. (2023) · Sensors · doi:10.3390/s23136202 · Cited by 83
Underwater Robots and Key Technologies for Operation Control
Sun, L., Wang, Y., Hui, X., Ma, X., Bai, X., & Tan, M. H. (2024) · Cyborg and Bionic Systems · doi:10.34133/cbsystems.0089 · Cited by 92
“The commonly utilized vision-based technology in the underwater environment is visual Simultaneous Location and Mapping (SLAM) [80].”
MethodReal-Time Visual–Inertial SLAM Based on Adaptive Keyframe Selection for Mobile AR Applications
Piao, J.-C., & Kim, S. (2019) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2019.2913324 · Cited by 83
“For instance, the ORB feature extraction operation in ORB-SLAM [18] requires at least about 20 ms per frame to run on a computer, and this time exceeds 100 ms on a mobile device.”
MethodInfluentialAppearance-invariant place recognition by discriminatively training a convolutional neural network
López-Antequera, M., Gomez-Ojeda, R., Petkov, N., & González-Jiménez, J. (2017) · Pattern Recognition Letters · doi:10.1016/j.patrec.2017.04.017 · Cited by 80
CarFusion: Combining Point Tracking and Part Detection for Dynamic 3D Reconstruction of Vehicles
Reddy, N. D., Vo, M., & Narasimhan, S. G. (2018) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2018.00204 · Cited by 100
“On the other hand, there has also been significant work on tracking feature points [38, 1] in structure-from-motion approaches applied to a video from a single moving camera [20, 31, 11, 30].”
BackgroundAn overview of deep learning methods for image registration with focus on feature-based approaches
Kuppala, K., Banda, S., & Barige, T. R. (2020) · International Journal of Image and Data Fusion · doi:10.1080/19479832.2019.1707720 · Cited by 74
A Novel Lidar-Assisted Monocular Visual SLAM Framework for Mobile Robots in Outdoor Environments
Yin, J., Luo, D., Yan, F., & Zhuang, Y. (2022) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2022.3190031 · Cited by 85
Efficient Non-Consecutive Feature Tracking for Robust Structure-From-Motion
Zhang, G., Liu, H., Dong, Z., Jia, J., Wong, T., & Bao, H. (2016) · IEEE Transactions on Image Processing · doi:10.1109/tip.2016.2607425 · Cited by 77
“The methods of [48] and [49] can close loops efficiently”
MethodInfluentialIndoor Relocalization in Challenging Environments With Dual-Stream Convolutional Neural Networks
Li, R., Liu, Q., Gui, J., Gu, D., & Hu, H. (2017) · IEEE Transactions on Automation Science and Engineering · doi:10.1109/tase.2017.2664920 · Cited by 80
“In the future, we would like to use features learned from the dual-stream CNN instead of handcrafted features in SLAM to expand to the application of visual localization.”
MethodInfluentialRobust Object-based SLAM for High-speed Autonomous Navigation
Ok, K., Liu, K., Frey, K. M., How, J. P., & Roy, N. (2019) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2019.8794344 · Cited by 85
“In this section, we first discuss the strengths of our landmark representation then formulate our object-based SLAM problem.”
BackgroundMethodInfluentialGood Feature Matching: Toward Accurate, Robust VO/VSLAM With Low Latency
Zhao, Y., & Vela, P. A. (2020) · IEEE Transactions on Robotics · doi:10.1109/tro.2020.2964138 · Cited by 87
“, ORB-SLAM [3], OKVIS [19]) benefit from long-baseline feature matchings, and are accurate and robust in”
BackgroundMethodInfluentialChen, Z., Liu, X., Kojima, M., Huang, Q., & Arai, T. (2021) · Sensors · doi:10.3390/s21041536 · Cited by 84
“Visual SLAM, including Monocular, Stereo, RGB-D cameras, and Lidars, has shown significant advantages in intelligent mobile robots and autonomous vehicles because of robustness, intelligence, and Some SLAM schemes, such as ORB-SLAM [7,8], LSD-SLAM [9], ElasticFusion [10], and SVO [11], are mature. adaption.”
BackgroundInfluentialLearned Visual Navigation for Under-Canopy Agricultural Robots
Sivakumar, A. N. V., Modi, S., Gasparino, M. V., Ellis, C., Velasquez, A. E. B., Chowdhary, G. V., & Gupta, S. (2021) · Robotics: Science and Systems · doi:10.15607/rss.2021.xvii.019 · Cited by 103
“Importance of semantics precludes the use of traditional methods that infer geometry from monocular RGB image streams [45, 23].”
MethodRobust Place Recognition using an Imaging Lidar
Shan, T., Englot, B., Duarte, F., Ratti, C., & Rus, D. L. (2021) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra48506.2021.9562105 · Cited by 90
“We utilize DBoW [5] to convert the ORB feature descriptors O into a bag-of-words vector using the visual vocabulary proposed in [3].”
Method3D Surveying of Underground Built Heritage: Opportunities and Challenges of Mobile Technologies
Stefano, F. D., Torresani, A., Farella, E. M., Pierdicca, R., Menna, F., & Fabio Remondino, A. (2021) · Sustainability · doi:10.3390/su132313289 · Cited by 89
Unsupervised Homography Estimation with Coplanarity-Aware GAN
Hong, M., Lu, Y., Ye, N., Lin, C., Zhao, Q., & Liu, S. (2022) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52688.2022.01714 · Cited by 87
“Homography estimation is a fundamental computer vision problem that plays an important role in a wide range of applications, such as image/video stitching [14,37], camera calibration [40], HDR imaging [12] and SLAM [24, 41].”
Climbing robots for manufacturing
Tao, B., Gong, Z., & Ding, H. (2023) · National Science Review · doi:10.1093/nsr/nwad042 · Cited by 79
“In fact, many similar localization methods have the potential to be applied in climbing robots for manufacturing, such as feature-based monocular ORB-SLAM [109].”
BackgroundComparison of ROS-based visual SLAM methods in homogeneous indoor environment
Ibragimov, I. Z., & Afanasyev, I. M. (2017) · Workshop on Positioning, Navigation and Communications (WPNC) · doi:10.1109/wpnc.2017.8250081 · Cited by 83
“Monocular ORB-SLAM method ORB-SLAM8 is a feature-based real-time SLAM library for monocular, stereo and RGB-D cameras [9].”
MethodEKF-Based Visual Inertial Navigation Using Sliding Window Nonlinear Optimization
Heo, S., Cha, J., & Park, C. G. (2018) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2018.2866637 · Cited by 77
“Visual SLAM is a technique that simultaneously estimates both the vehicular motion and the surrounding environment, and this is generally based on optimization techniques over multiple keyframes [12].”
MethodHigh-resolution real-time 360∘ 3D surface defect inspection with fringe projection profilometry
Qian, J., Feng, S., Xu, M., Tao, T., Shang, Y., Chen, Q., & Zuo, C. (2020) · Optics and Lasers in Engineering · doi:10.1016/j.optlaseng.2020.106382 · Cited by 83
Improved RRT-Connect Based Path Planning Algorithm for Mobile Robots
Chen, J., Zhao, Y., & Xu, X. (2021) · IEEE Access · doi:10.1109/access.2021.3123622 · Cited by 78
Mobile Robot Navigation Using Deep Reinforcement Learning
Lee, M. R., & Yusuf, S. H. (2022) · Processes · doi:10.3390/pr10122748 · Cited by 91
Multi-rotor drone tutorial: systems, mechanics, control and state estimation
Yang, H., Lee, Y., Jeon, S.-Y., & Lee, D. (2017) · Intelligent Service Robotics · doi:10.1007/s11370-017-0224-y · Cited by 85
“, ORB-SLAM [78], graph-SLAM [79], LSDSLAM [80], dense-SLAM [81]), which is a topic of active research currently being pursued by many research labs and groups.”
BackgroundRecchiuto, C. T., & Sgorbissa, A. (2017) · Journal of Field Robotics · doi:10.1002/rob.21756 · Cited by 86
Loop closure detection for visual SLAM systems using convolutional neural network
Zhang, X., Su, Y. L., & Zhu, X. (2017) · International Conference on Automation and Computing (ICAC) · doi:10.23919/iconac.2017.8082072 · Cited by 79
“The visual simultaneous localization and mapping (SLAM) has generated considerable research interest and has been extensively investigated in the past years both in robotics [1], [2] and computer vision communities [3].”
BackgroundMonocular Depth Prediction Using Generative Adversarial Networks
Kumar, A. C. S., Bhandarkar, S. M., & Prasad, M. (2018) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw.2018.00068 · Cited by 84
“Reconstruction traditionally adopted approaches motivated by the physics of image formation from 3D either based on finding consistent 2D matches that yield good reconstruction (triangulation) [25, 12, 20] or proposing”
Overview of Image Matching Based on ORB Algorithm
Luo, C. W., Yang, W. P., Huang, P., & Zhou, J. W. (2019) · Journal of Physics Conference Series · doi:10.1088/1742-6596/1237/3/032020 · Cited by 71
Zero-Shot Depth Estimation From Light Field Using A Convolutional Neural Network
Peng, J., Xiong, Z., Wang, Y., Zhang, Y., & Liu, D. (2020) · IEEE Transactions on Computational Imaging · doi:10.1109/tci.2020.2967148 · Cited by 71
“Conventional depth from video methods such as SFM [40], OEB-SLAM [41] and DTAM [42], explore the scene geometry from images taken from different positions.”
MethodShariq, M. H., & Hughes, B. R. (2020) · Renewable and Sustainable Energy Reviews · doi:10.1016/j.rser.2020.109979 · Cited by 86
A Comprehensive Study of 3-D Vision-Based Robot Manipulation
Cong, Y., Chen, R., Ma, B., Liu, H., Hou, D., & Yang, C. (2021) · IEEE Transactions on Cybernetics · doi:10.1109/tcyb.2021.3108165 · Cited by 96
“D images, such as SIFT [39], SURF [40], ORB [41], or machine-learning-based feature descriptors, for example, PCA-SIFT [42] and LDAHash [43]; and for rich 3-”
MethodMarshall, J. A., Sun, W., & L’Afflitto, A. (2021) · Annual Reviews in Control · doi:10.1016/j.arcontrol.2021.10.013 · Cited by 85
“One is the indirect or feature-based approach (Klein & Murray, 2007; Mur-Artal et al., 2015; Mur-Artal & Tardos, 2017), which is based on key-point matching and builds a sparsely reconstructed map of the environment.”
BackgroundInfluentialLin, J., & Zhang, F. (2024) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2024.3456473 · Cited by 101
“Following this idea, a more complete and reliable framework ORB-SLAM [28] was proposed.”
MethodA non-rigid map fusion-based direct SLAM method for endoscopic capsule robots
Turan, M., Almalioglu, Y., Araujo, H., Konukoğlu, E., & Sitti, M. (2017) · International Journal of Intelligent Robotics and Applications · doi:10.1007/s41315-017-0036-4 · Cited by 83
“en frames. Indirect methods were introduced to reduce the computational complexity and achieve real time processing time. This is achieved by using sparse feature points instead all pixel information [22]. Features are expected to be distinctive and invariant to viewpoint and illumination changes, as well as resilient…”
MethodRGB-T SLAM: A flexible SLAM framework by combining appearance and thermal information
Chen, L. F., Sun, L., Yang, T., Fan, L., Huang, K., & Xuanyuan, Z. (2017) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2017.7989668 · Cited by 82
“In order to compare RGB-T SLAM, ORB-SLAM [7], LSD-SLAM [5] and PTAM [3] with the ground truth, we align the keyframe trajectories using a similarity transformation, as scale is unknown, and measure the absolute trajectory error.”
BackgroundMethodInfluentialEnhanced UAV Indoor Navigation through SLAM-Augmented UWB Localization
Tiemann, J., Ramsey, A., & Wietfeld, C. (2018) · IEEE International Conference on Communications workshops · doi:10.1109/iccw.2018.8403539 · Cited by 82
“monocular [21], stereo and RGB-D cameras [22] developed by Mur-Artal et.”
BackgroundLoosely-Coupled Semi-Direct Monocular SLAM
Lee, S. H., & Civera, J. (2018) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2018.2889156 · Cited by 81
“Although this system is highly efficient, it was shown to be less robust [9], [24] than ORBSLAM [11] and DSO [6].”
BackgroundMethodInfluentialSalientDSO: Bringing Attention to Direct Sparse Odometry
Liang, H.-J., Sanket, N. J., Fermuller, C. M., & Aloimonos, Y. (2019) · IEEE Transactions on Automation Science and Engineering · doi:10.1109/tase.2019.2900980 · Cited by 75
“t, a multi-scale image pyramid and a constant motion model. If tracking fails, SalientDSO attempts to recover the motion by trying 27 different small rotations. Keyframe Creation: Similar to ORB-SLAM [5], SalientDSO initially takes many keyframes (around 5-10 keyframes per second), and then sparsifies them by early mar…”
MethodAn Overview of Key SLAM Technologies for Underwater Scenes
Wang, X., Fan, X., Shi, P., Ni, J., & Zhou, Z. (2023) · Remote Sensing · doi:10.3390/rs15102496 · Cited by 80
LiDAR, IMU, and camera fusion for simultaneous localization and mapping: a systematic review
Fan, Z., Zhang, L., Wang, X., Shen, Y., & Deng, F. Y. (2025) · Artificial Intelligence Review · doi:10.1007/s10462-025-11187-w · Cited by 110
Unsupervised Odometry and Depth Learning for Endoscopic Capsule Robots
Turan, M., Örnek, E. P., Ibrahimli, N., Giracoglu, C., Almalıoğlu, Y., Yanik, M. F., & Sitti, M. (2018) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2018.8593623 · Cited by 81
A Robust RGB-D SLAM System With Points and Lines for Low Texture Indoor Environments
Fu, Q., Yu, H., Lai, L., Wang, J., Xia, P., Sun, W. J., & Sun, M. (2019) · IEEE Sensors Journal · doi:10.1109/jsen.2019.2927405 · Cited by 75
Ground-Plane-Based Absolute Scale Estimation for Monocular Visual Odometry
Zhou, D., Dai, Y., & Li, H. (2019) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2019.2900330 · Cited by 76
“Stereo camera [3], [24]–[27] is also an important sensor for VO and SLAM.”
BackgroundPanoramic SLAM from a multiple fisheye camera rig
Ji, S., Qin, Z., Shan, J., & Lü, M. (2019) · ISPRS Journal of Photogrammetry and Remote Sensing · doi:10.1016/j.isprsjprs.2019.11.014 · Cited by 83
FutureMapping: The Computational Structure of Spatial AI SystemsPreprint
Davison, A. J. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1803.11288 · Cited by 103
“…been more meaningfully represented by the progress of high quality real-time open source SLAM reseach systems (e.g. MonoSLAM [8, 10], PTAM [24], KinectFusion [41], LSD-SLAM [12], ORB-SLAM [36], OKVIS [28], SVO [14], ElasticFusion [56]) that people can experiment with, rather than benchmarks.”
BackgroundAn Evaluation of Feature Matchers for Fundamental Matrix Estimation
Bian, J.-W., Wu, Y.-H., Zhao, J. Y., Liu, Y., Zhang, L., Cheng, M., & Reid, I. D. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1908.09474 · Cited by 46
Pseudo RGB-D for Self-improving Monocular SLAM and Depth Prediction
Tiwari, L., Ji, P., Tran, Q.-H., Zhuang, B., Anand, S., & Chandraker, M. K. (2020) · Lecture notes in computer science · doi:10.1007/978-3-030-58621-8_26 · Cited by 80
FroDO: From Detections to 3D Objects
Rünz, M., Li, K., Tang, M., Ma, L., Kong, C., Schmidt, T., Reid, I. D., Agapito, L., Straub, J., Lovegrove, S. J., et al. (2020) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr42600.2020.01473 · Cited by 97
AirDOS: Dynamic SLAM benefits from Articulated Objects
Qiu, Y., Wang, C., Wang, W., Henein, M., & Scherer, S. (2022) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra46639.2022.9811667 · Cited by 92
“For example, ORB-SLAM [3] applies RANSAC to select and remove points that cannot converge to a stable pose estimation.”
InfluentialVisual Place Recognition: A Tutorial [Tutorial]
Schubert, S., Neubert, P., Garg, S., Milford, M. J., & Fischer, T. (2023) · IEEE Robotics & Automation Magazine · doi:10.1109/mra.2023.3310859 · Cited by 102
“…of such a topological SLAM system is FAB-MAP [9], also referred to as ‘appearance-only SLAM’, where loop closure generation is based on appearance only (i.e., images), thus different from 3D/metric SLAM systems such as ORB-SLAM [10] where the map and the visual landmarks are expressed in 3D.”
BackgroundPhotometric Bundle Adjustment for Vision-Based SLAM
Alismail, H., Brett Browning, A., & Lucey, S. (2017) · Lecture notes in computer science · doi:10.1007/978-3-319-54190-7_20 · Cited by 84
“10 in comparison with ORB-SLAM [18], which we used its pose output to initialize our algorithm.”
MethodInfluentialTightly-Coupled Monocular Visual-Odometric SLAM Using Wheels and a MEMS Gyroscope
Quan, M., Piao, S., Tan, M., & Huang, S.-S. (2019) · IEEE Access · doi:10.1109/access.2019.2930201 · Cited by 74
“Our monocular VOSLAM system is inspired by ORBSLAM [14] andORB-VISLAM [5].”
BackgroundMethodInfluentialSequential Adversarial Learning for Self-Supervised Deep Visual Odometry
Li, S., Xue, F., Wang, X., Yan, Z., & Zha, H. (2019) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2019.00294 · Cited by 80
“It is traditionally solved by minimizing photometric [12] or geometric [29] reprojection errors and works well in regular environments, but fails in challenging conditions like dynamic objects and abrupt motions.”
BackgroundMethodPhotometric Mesh Optimization for Video-Aligned 3D Object Reconstruction
Lin, C.-H., Wang, O., Russell, B. C., Shechtman, E., Kim, V. G., Fisher, M., & Lucey, S. (2019) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2019.00106 · Cited by 79
“Most approaches begin by estimating camera coordinates using 2D keypoint matching, a process known as SLAM [10, 29] or SfM [12, 32], followed by dense reconstruction methods such as MVS [13] and meshing [22].”
Detecting Deficient Coverage in Colonoscopies
Freedman, D., Blau, Y., Katzir, L., Aides, A., Shimshoni, I., Veikherman, D., Golany, T., Gordon, A., Corrado, G., Matias, Y., et al. (2020) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2020.2994221 · Cited by 64
“clude by briefly surveying the literature related to recent techniques in SLAM, visual odometry, and depth reconstruction intended for the broader computer vision audience. Earlier work, such as [29], [30], [31], was geometric in character, and did not use any sort of learning pipeline. Initial work which applied deep…”
MethodLightweight 3-D Localization and Mapping for Solid-State LiDAR
Wang, H., Wang, C., & Xie, L. (2021) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2021.3060392 · Cited by 71
“SLAM system such as visual SLAM [6], [7] and visual inertial SLAM [8], [9].”
Vision-Based Mobile Robotics Obstacle Avoidance With Deep Reinforcement Learning
Wenzel, P., Schön, T., Leal-Taixé, L., & Cremers, D. (2021) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra48506.2021.9560787 · Cited by 77
“Typically, in robotic navigation problems, simultaneous localization and mapping (SLAM) [1], [2], [3] algorithms are a fundamental part of such a system.”
BackgroundExternal multi-modal imaging sensor calibration for sensor fusion: A review
Qiu, Z., Martínez-Sánchez, J., Arias, P., & Rashdi, R. (2023) · Information Fusion · doi:10.1016/j.inffus.2023.101806 · Cited by 77
DytanVO: Joint Refinement of Visual Odometry and Motion Segmentation in Dynamic Environments
Shen, S., Cai, Y., Wang, W., & Scherer, S. (2023) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra48891.2023.10161306 · Cited by 94
“We provide the performance of AirDOS and ORB-SLAM [39] after masking the dynamic features during their ego-motion estimation.”
MethodBTC: A Binary and Triangle Combined Descriptor for 3-D Place Recognition
Yuan, C., Lin, J., Liu, Z., Wei, H., Hong, X., & Zhang, F. (2024) · IEEE Transactions on Robotics · doi:10.1109/tro.2024.3353076 · Cited by 98
“By reducing drift in pose estimation and enabling relocalization, it proves indispensable in robotic applications, particularly within simultaneous localization and mapping (SLAM) systems such as visual SLAM [1], [2] and LiDAR SLAM [3], [4], where accurate and reliable navigation is necessary.”
BackgroundWang, S., & Ahmad, N. S. (2024) · IEEE Access · doi:10.1109/access.2024.3519874 · Cited by 93
“Cameras: Monocular cameras [62] use a single lens to capture images, providing two-dimensional imagery without depth information, and cannot directly measure the depth of objects.”
Huang, W., & Liu, H. (2018) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2018.8460206 · Cited by 78
“It can be seen that in spite of the extrinsic parameters are unknown in our method, the RMSE error of our method is not much worse than VI ORB-SLAM.”
MethodInfluentialTrifo-VIO: Robust and Efficient Stereo Visual Inertial Odometry Using Points and Lines
Zheng, F., Tsai, G., Zhang, Z., Liu, S., Chu, C.-C., & Hu, H. (2018) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2018.8594354 · Cited by 75
Structure Aware SLAM Using Quadrics and Planes
Hosseinzadeh, M., Latif, Y., Pham, T. T., Sünderhauf, N., & Reid, I. D. (2019) · Lecture notes in computer science · doi:10.1007/978-3-030-20893-6_26 · Cited by 75
Liu, J., Gao, W., & Hu, Z. (2019) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros40897.2019.8967607 · Cited by 77
“Compared with visual odometry (VO) such as ORB-SLAM [4] that only relies on camera, VIO algorithms are not only able to determine the absolute scale, pitch and roll, but also much more robust than VO in textureless regions.”
MethodImproving Virtual Reality Ergonomics Through Reach-Bounded Non-Linear Input Amplification
Wentzel, J., d'Eon, G., & Vogel, D. (2020) · CHI Conference on Human Factors in Computing Systems · doi:10.1145/3313831.3376687 · Cited by 68
“Some newer VR headsets track head position without external sensors or beacons by using in-headset cameras and SLAM algorithms [20].”
BackgroundPSPNet-SLAM: A Semantic SLAM Detect Dynamic Object by Pyramid Scene Parsing Network
Long, X., Zhang, W., & Zhao, B. (2020) · IEEE Access · doi:10.1109/access.2020.3041038 · Cited by 70
“…of visual SLAM has attracted a large number of researchers with emergence of many excellent SLAM system frameworks such as MonoSLAM [1], ORB-SLAM [2], ORB-SLAM2 [3], LSD-SLAM [4], SVO [5], DynaSLAM [6], which can achieve satisfactory performance while mobile robots are used in a static…”
MethodZero-Shot Everything Sketch-Based Image Retrieval, and in Explainable Style
Lin, F., Li, M., Li, D., Hospedales, T. M., Song, Y.-Z., & Qi, Y. (2023) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52729.2023.02236 · Cited by 91
“Learning dense visual correspondence is an essential component and it has been actively explored in many vision tasks, such as structure-from-motion (SfM) [48], visual localization [38],”
BackgroundA comprehensive overview of core modules in visual SLAM framework
Cai, D., Li, R., Hu, Z., Lu, J., Li, S., & Zhao, Y. (2024) · Neurocomputing · doi:10.1016/j.neucom.2024.127760 · Cited by 75
Relocalization, Global Optimization and Map Merging for Monocular Visual-Inertial SLAM
Qin, T., Li, P., & Shen, S. (2018) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2018.8460780 · Cited by 75
The IPIN 2019 Indoor Localisation Competition—Description and Results
Potortì, F., Park, S., Crivello, A., Palumbo, F., Girolami, M., Barsocchi, P., Lee, S., Torres-Sospedra, J., Jiménez, A. R., Pérez-Navarro, A., et al. (2020) · IEEE Access · doi:10.1109/access.2020.3037221 · Cited by 68
“Our vSLAM implementation is based on monocular SLAM using keyframes and keypoints [25].”
MethodBridge Inspection Using Unmanned Aerial Vehicle Based on HG-SLAM: Hierarchical Graph-Based SLAM
Jung, S., Choi, D., Song, S., & Myung, H. (2020) · Remote Sensing · doi:10.3390/rs12183022 · Cited by 68
“In recent years, researchers have become interested in implementing either visual SLAM or odometry in the absence of GPS signals; examples of the corresponding methods include parallel tracking and mapping (PTAM) [28], large-scale direct SLAM (LSD-SLAM) [29], oriented FAST and rotated BRIEF SLAM (ORB-SLAM) [30], semid…”
BackgroundQiu, K., Qin, T., Pan, J., Liu, S., & Shen, S. (2020) · IEEE Transactions on Robotics · doi:10.1109/tro.2020.3033698 · Cited by 77
“For calibration between an IMU and a monocular camera, we use ORB-SLAM [13] as the ego-motion estimation method for the monocular camera.”
BackgroundMethodInfluentialVox-Surf: Voxel-Based Implicit Surface Representation
Li, H., Yang, X., Zhai, H., Liu, Y., Bao, H., & Zhang, G. (2022) · IEEE Transactions on Visualization and Computer Graphics · doi:10.1109/tvcg.2022.3225844 · Cited by 97
“These prerequi-sites can be easily obtained from some existing SLAM [29], [30] or SfM [1] methods.”
MethodSDV-LOAM: Semi-Direct Visual–LiDAR Odometry and Mapping
Yuan, Z., Wang, Q., Cheng, K., Hao, T., & Yang, X. Y. (2023) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2023.3262817 · Cited by 88
“In general, vision-based odometry/SLAM systems can be categorized into three classes: 1) feature-based methods [1], [25], [26], [27], [28] which rely on local image features for pose tracking, 2) direct methods [2], [3], [6], [7], [29] which directly use raw sensor measurements (e.g., intensity…”
MethodEfficient and Consistent Bundle Adjustment on Lidar Point Clouds
Liu, Z., Liu, X., & Zhang, F. (2023) · IEEE Transactions on Robotics · doi:10.1109/tro.2023.3311671 · Cited by 88
“Compared to visual BA, which has been well-established in photogrammetry and played a fundamental role in various vital applications, including visual odometry (VO) [23], [24], [25], visual-inertial odometry (VIO) [26], [27], 3-”
Method3D Reconstruction with Spatial Memory
Wang, H., & Agapito, L. (2025) · International Conference on 3D Vision (3DV) · doi:10.1109/3dv66043.2025.00013 · Cited by 356
“Given the calibrated cameras, visual SLAM can perform sparse [21, 28, 41, 52] or dense [27, 54] reconstruction via minimizing either reprojection error (indirect) [21, 41, 52] or photometric error (direct) [27, 28, 54].”
SLAMBench2: Multi-Objective Head-to-Head Benchmarking for Visual SLAM
Bodin, B., Wagstaff, H., Saecdi, S., Nardi, L., Vespa, E., Mawer, J., Nisbet, A. P., Luján, M., Furber, S. B., Davison, A. J., et al. (2018) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2018.8460558 · Cited by 79
Whole Stomach 3D Reconstruction and Frame Localization From Monocular Endoscope Video
Widya, A. R., Monno, Y., Okutomi, M., Suzuki, S., Gotoda, T., & Miki, K. (2019) · IEEE Journal of Translational Engineering in Health and Medicine · doi:10.1109/jtehm.2019.2946802 · Cited by 66
“[15] O. G. Grasa, E. Bernal, S. Casado, I. Gil, and J. M. M. Montiel, ‘‘Visual SLAM for handheld monocular endoscope,’’ IEEE Trans.”
MethodInfluentialA Survey on Visual Navigation and Positioning for Autonomous UUVs
Qin, J., Li, M., Li, D., Zhong, J., & Yang, K. (2022) · Remote Sensing · doi:10.3390/rs14153794 · Cited by 65
“Tightly-coupled methods combine the data of the vision sensor and the IMU through optimization and filtering to jointly construct the motion equation, so as to obtain the final pose information by considering the state estimation of the two kinds of data.”
MethodCollaborative Semantic Understanding and Mapping Framework for Autonomous Systems
Yue, Y., Zhao, C., Wu, Z., Yang, C., Wang, Y., & Wang, D. (2020) · IEEE/ASME Transactions on Mechatronics · doi:10.1109/tmech.2020.3015054 · Cited by 70
“Current approaches mainly consists of Lidar SLAM [10], visual SLAM [11], and graph SLAM [12].”
MethodSanchez-Cuevas, P. J., González-Morgado, A., Cortes, N., Gayango, D. B., Jimenez-Cano, A. E., Ollero, A., & Heredia, G. (2020) · Sensors · doi:10.3390/s20174708 · Cited by 68
“Moreover, although there are several solutions that aim to solve this localization problem in a GNSS-denied environment, those usually consist of algorithms that generate a local reference frame each time they are executed, like the classical VSLAM [44], LOAM [50], and other SLAM algorithms [51].”
BackgroundAn Integrated Visual Odometry System for Underwater Vehicles
Xu, Z., Haroutunian, M., Murphy, A. J., Neasham, J. A., & Norman, R. A. (2020) · IEEE Journal of Oceanic Engineering · doi:10.1109/joe.2020.3036710 · Cited by 68
“It 88 is a reliable and complete solution for monocular SLAM [18].”
BackgroundDV-LOAM: Direct Visual LiDAR Odometry and Mapping
Wang, W., Liu, J., Wang, C., Luo, B., & Zhang, C. (2021) · Remote Sensing · doi:10.3390/rs13163340 · Cited by 74
“It is worth mentioning that this similar strategy is widely used in various SLAM methods, including direct [11,12] and indirect methods [8,9].”
BackgroundMethodResultBinocular video-based 3D reconstruction and length quantification of cracks in concrete structures
Deng, L., Sun, T., Yang, L., & Cao, R. (2023) · Automation in Construction · doi:10.1016/j.autcon.2023.104743 · Cited by 72
EgoLocate: Real-time Motion Capture, Localization, and Mapping with Sparse Body-mounted Sensors
Yi, X., Zhou, Y., Habermann, M., Golyanik, V., Pan, S., Theobalt, C., & Xu, F. (2023) · ACM Transactions on Graphics · doi:10.1145/3592099 · Cited by 90
“The SLAM module needs a monocular initialization, where the initial map points are triangulated by computing the relative pose between two frames based on the homography or the fundamental matrix [Mur-Artal et al. 2015].”
MethodSwitch-SLAM: Switching-Based LiDAR-Inertial-Visual SLAM for Degenerate Environments
Lee, J., Komatsu, R., Shinozaki, M., Kitajima, T., Asama, H., An, Q., & Yamashita, A. (2024) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2024.3421792 · Cited by 79
“Conversely, visual SLAM [4], [5], [6] face challenges in scenarios involving aggressive motions, rapidly changing light conditions, and texture-less environments.”
BackgroundGround-Level Mapping and Navigating for Agriculture Based on IoT and Computer Vision
Zhao, W., Wang, X., Qi, B., & Runge, T. M. (2020) · IEEE Access · doi:10.1109/access.2020.3043662 · Cited by 65
“The first is a feature-based solu-tion, where the inconsistency of image features in sequential image streams is used to recognize camera movement, for example, Mono SLAM [20], PTAM [21] and ORB-SLAM [22].”
BackgroundMovement science needs different pose tracking algorithms
Seethapathi, N., Wang, S., Saluja, R., Blohm, G., & Kording, K. P. (2019) · arXiv · doi:10.48550/arxiv.1907.10226 · Cited by 64
“Additionally, pose tracking algorithms could be trained to use a fixed background object to estimate and remove camera movements from the pose estimates, say, by using SLAM and self calibration to update camera pose [90].”
MethodLearning Single-Image Depth From Videos Using Quality Assessment Networks
Chen, W., Qian, S., & Deng, J. (2019) · 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2019.00575 · Cited by 65
“However, to implement such an approach in practice, there remains a significant technical hurdle—despite great successes [1, 19, 36, 37, 30], existing SfM systems are still far from reliable when applied to arbitrary Internet videos.”
Background
Metadata
- Authors
- Mur-Artal, R., Montiel, J. M. M., & Tardos, J. D.
- Affiliations
- Universidad de Zaragoza (ES)
- Venue
- IEEE Transactions on Robotics
- Published
- 2015-10
- Volume
- 31
- Issue
- 5
- Pages
- 1147-1163
- ISSN
- 1552-3098 (ISSN-L)
- 1941-0468
- OpenAlex
- W1612997784
- Cited by
- 6,778
- References
- 46
- Citations by year
- 2026: 441 · 2025: 784 · 2024: 857 · 2023: 847 · 2022: 776 · 2021: 738 · 2020: 672 · 2019: 653 · 2018: 528 · 2017: 353 · 2016: 119 · 2015: 10
- FWCI
- 487.97
- Type
- journal article
- Language
- en
- Open access
- green
- arxiv.org
- Locations
- IEEE Transactions on Robotics (publishedVersion)
- arXiv (Cornell University) (submittedVersion)
- arXiv (Cornell University)
- Funders
- Dirección General de Investigación of Spain (DPI2012-32168)
- Ministerio de Educación Scholarship (FPU13/04175)
- Gobierno de Aragón Scholarship (B121/13)
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Robotics and Sensor-Based Localization
- Physical Sciences › Earth and Planetary Sciences › Geology › 3D Surveying and Cultural Heritage
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Image and Video Retrieval Techniques
- Keywords
- ORB-SLAM, monocular SLAM, SLAM, feature-based SLAM, real-time SLAM, loop closure, relocalization, survival of the fittest, keyframe selection, automatic initialization, indoor and outdoor environments
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.