The DOI matches its Crossref record; 20 of the 21 references it cites were found in a registry or an index.
ORB-SLAM2: An Open-Source SLAM System for Monocular, Stereo, and RGB-D Cameras
Open accessAbstract
We present ORB-SLAM2, a complete simultaneous localization and mapping (SLAM) system for monocular, stereo and RGB-D cameras, including map reuse, loop closing, and relocalization capabilities. The system works in real time on standard central processing units in a wide variety of environments from small hand-held indoors sequences, to drones flying in industrial environments and cars driving around a city. Our back-end, based on bundle adjustment with monocular and stereo observations, allows for accurate trajectory estimation with metric scale. Our system includes a lightweight localization mode that leverages visual odometry tracks for unmapped regions and matches with map points that allow for zero-drift localization. The evaluation on 29 popular public sequences shows that our method achieves state-of-the-art accuracy, being in most cases the most accurate SLAM solution. We publish the source code, not only for the benefit of the SLAM community, but with the aim of being an out-of-the-box SLAM solution for researchers in other fields.
Overview
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
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?
The check wasn’t confident either way, so it gives no verdict — never disputed.
In the citing paper
“As an input-driven system, the stochastic input sequences of edge-assisted SLAM cause a considerable impact on the state dynamics and rewards, which then incur high variance during the training of policy gradient methods [13], [14].”
From Orchestrating Joint Offloading and Scheduling for Low-Latency Edge SLAM (2025) · cites this paper as [14]
Experimental — accuracy not yet measuredThe check wasn’t confident either way, so it gives no verdict — never disputed.
In the citing paper
“In such an input-driven system, traditional state-dependent DRL algorithms suffer from high state dynamics, leading to inherent bias in policy gradient estimates and increased gradient variance during training [13], [14].”
From Orchestrating Joint Offloading and Scheduling for Low-Latency Edge SLAM (2025) · cites this paper as [14]
Experimental — accuracy not yet measured
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
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 1×
“The system uses the same ORB features [17] for tracking, mapping, and place recognition tasks.”
MethodVision 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×
“We use two different metrics, the absolute translation root-mean-square error (RMSE) tabs proposed in [3], and the average relative translation trel and rotation rrel errors proposed in [2].”
BackgroundMethodORB-SLAM: A Versatile and Accurate Monocular SLAM System
Mur-Artal, R., Montiel, J. M. M., & Tardos, J. D. (2015) · IEEE Transactions on Robotics · doi:10.1109/tro.2015.2463671 · Cited by 6,778 · cited 7×
“Left: Monocular ORB-SLAM [1], right: ORB-SLAM2 (stereo).”
BackgroundMethodResultInfluentialSelf-citationA benchmark for the evaluation of RGB-D SLAM systems
Sturm, J., Engelhard, N., Endres, F., Burgard, W., & Cremers, D. (2012) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2012.6385773 · Cited by 4,230 · cited 4×
“The RGB-D case shows the keyframe poses estimated in sequence fr1_room from the TUM RGB-D Dataset [3], and a dense pointcloud, rendered by backprojecting sensor depth maps from the estimated keyframe poses.”
MethodInfluentialKinectFusion: Real-time dense surface mapping and tracking
Newcombe, R. A., Fitzgibbon, A., Izadi, S., Hilliges, O., Molyneaux, D., Kim, D., Davison, A. J., Kohi, P., Shotton, J., & Hodges, S. (2011) · 2011 10th IEEE International Symposium on Mixed and Augmented Reality · doi:10.1109/ismar.2011.6092378 · Cited by 4,008 · cited 2×
“Note that our SLAM does not perform any fusion like KinectFusion [4] or similar, but the good definition indicates the accuracy of the keyframe poses.”
BackgroundThe EuRoC micro aerial vehicle datasets
Burri, M., Nikolic, J., Gohl, P., Schneider, T., Rehder, J., Omari, S., Achtelik, M., & Siegwart, R. (2016) · The International Journal of Robotics Research · doi:10.1177/0278364915620033 · Cited by 2,086 · cited 1×
“The recent EuRoC dataset [21] contains 11 stereo sequences recorded from a microaerial vehicle (MAV) flying around two different rooms and a large industrial environment.”
BackgroundBags of Binary Words for Fast Place Recognition in Image Sequences
Gálvez‐López, D., & Tardós, J. D. (2012) · IEEE Transactions on Robotics · doi:10.1109/tro.2012.2197158 · Cited by 1,890 · cited 2×
“The system has embedded a Place Recognition module based on DBoW2 [16] for relocalization, in case of tracking failure (e.g. an occlusion) or for reinitialization in an already mapped scene, and for loop detection.”
Dense visual SLAM for RGB-D cameras
Kerl, C., Sturm, J., & Cremers, D. (2013) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2013.6696650 · Cited by 941 · cited 5×
“In Table III we compare our accuracy to the following state-of-the-art methods: ElasticFusion [15], Kintinuous [12], DVO-SLAM [14] and RGB-D SLAM [13].”
MethodInfluential3-D Mapping With an RGB-D Camera
Endres, F., Hess, J., Sturm, J., Cremers, D., & Burgard, W. (2014) · IEEE Transactions on robotics · doi:10.1109/tro.2013.2279412 · Cited by 821 · cited 5×
“In Table III we compare our accuracy to the following state-of-the-art methods: ElasticFusion [15], Kintinuous [12], DVO-SLAM [14] and RGB-D SLAM [13].”
MethodInfluentialVisual-Inertial Monocular SLAM With Map Reuse
Mur-Artal, R., & Tardós, J. D. (2017) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2017.2653359 · Cited by 790 · cited 1×
“As shown in [22], this sequence can be processed using IMU information.”
MethodSelf-citation
Research works printed but not linked: 2
- 10.1177/0278364914551008 · DOI
- kuemmerle, 0, g2o: A general framework for graph optimization, Proc IEEE Int Conf Robot Autom, 3607
Cited by
Sorted by citations
Items 901–1,000 of 1,004
Privacy Preserving Visual SLAM
Shibuya, M., Sumikura, S., & Sakurada, K. (2020) · Lecture notes in computer science · doi:10.1007/978-3-030-58542-6_7 · Cited by 32
Learning Tactile Models for Factor Graph-based Estimation
Sodhi, P., Kaess, M., Mukadam, M., & Anderson, S. (2021) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra48506.2021.9561011 · Cited by 31
“These typically are analytic functions e.g. projection geometry for images [11, 12], or scan matching for point clouds [13, 14].”
BackgroundGEM: Online Globally Consistent Dense Elevation Mapping for Unstructured Terrain
Pan, Y., Xu, X., Ding, X., Huang, S., Wang, Y., & Xiong, R. (2020) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2020.3044338 · Cited by 31
“To solve this problem, we follow the local–global threads management mechanism in state-of-the-art SLAM systems, such as ORB-SLAM2 [2].”
BackgroundMethodPanoramic annular SLAM with loop closure and global optimization
Chen, H., Hu, W., Yang, K., Bai, J. Y., & Wang, K. (2021) · Applied Optics · doi:10.1364/ao.424280 · Cited by 31
Large-Scale LiDAR SLAM with Factor Graph Optimization on High-Level Geometric Features
Ćwian, K., Nowicki, M., Wietrzykowski, J., & Skrzypczyński, P. (2021) · Sensors · doi:10.3390/s21103445 · Cited by 31
“Such systems, such as ORB-SLAM2 [5], detect salient points in images, match these features to the map, and then further optimize their position, which results in accurate estimates of the camera pose.”
BackgroundMethodDevelopment of Modular Bio-Inspired Autonomous Underwater Vehicle for Close Subsea Asset Inspection
Gorma, W., Post, M. A., White, J., Gardner, J., Luo, Y., Kim, J., Mitchell, P., Morozs, N., Wright, M., & Xiao, Q. (2021) · Applied Sciences · doi:10.3390/app11125401 · Cited by 31
“While visual simultaneous localisation and mapping (SLAM) has seen impressive development for autonomous ground vehicles (AGVs) [31], unmanned aerial vehicles (UAVs) [32] and unmanned underwater vehicles [33], the technical challenges presented by underwater environments have hindered progress for AUVs, particularly i…”
BackgroundMethodChi, C., Wang, Q., Hao, T., Guo, P., & Yang, X. Y. (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/cvpr46437.2021.00249 · Cited by 32
“10 t err % r err ( o / 100) t err % r err ( o / 100) ORB-SLAM(full) [36] 2.51 0.26 2.10 0.48 ORB-SLAM2(stereo) [37] 0.82 – 0.58 – LSD-SLAM(stereo) [8] 1.22 Table 6.”
InfluentialEnergy-Efficient Ground Traversability Mapping Based on UAV-UGV Collaborative System
Li, J., Cheng, Y., Zhou, J., Chen, J., Liu, Z., Hu, S., & Leung, V. C. M. (2021) · IEEE Transactions on Green Communications and Networking · doi:10.1109/tgcn.2021.3107291 · Cited by 31
A Survey of 17 Indoor Travel Assistance Systems for Blind and Visually Impaired People
Wang, J., Liu, E., Geng, Y., Qu, X., & Wang, R. (2021) · IEEE Transactions on Human-Machine Systems · doi:10.1109/thms.2021.3121645 · Cited by 32
Real-Time Globally Consistent 3D Reconstruction With Semantic Priors
Huang, S.-S., Chen, H., Huang, J., Fu, H., & Hu, S. (2021) · IEEE Transactions on Visualization and Computer Graphics · doi:10.1109/tvcg.2021.3137912 · Cited by 31
“The main drawback of these approaches is that they only perform ego-motion (or bundle adjustment) with geometric cues, such as sparse [30], [31] or dense [1], [3], [5] landmarks.”
BackgroundData fusion based wireless temperature monitoring system applied to intelligent greenhouse
Xia, S., Nan, X., Cai, X., & Lu, X. (2021) · Computers and Electronics in Agriculture · doi:10.1016/j.compag.2021.106576 · Cited by 34
Integrated Task Sensing and Whole Body Control for Mobile Manipulation With Series Elastic Actuators
Ren, X., Liu, Y., Hu, Y., & Li, Z. (2022) · IEEE Transactions on Automation Science and Engineering · doi:10.1109/tase.2022.3156127 · Cited by 31
“ORB-SLAM2 is a feature-based system for real-time location and mapping, which can run in indoor and outdoor environments of various scales.”
BackgroundMethodInfluentialLi, Q., Xie, F., Zhao, J., Xu, B. H., Yang, J., Liu, X., & Suo, H. (2022) · Remote Sensing · doi:10.3390/rs14153720 · Cited by 33
3D-CALI: Automatic calibration for camera and LiDAR using 3D checkerboard
Wang, Q., Yan, C., Tan, R., Feng, Y., Sun, Y., & Liu, Y. (2022) · Measurement · doi:10.1016/j.measurement.2022.111971 · Cited by 30
Zhang, G., Qin, D., Yang, J., Yan, M., Tang, H., Bie, H., & Ma, L. (2022) · Remote Sensing · doi:10.3390/rs14236013 · Cited by 31
Wang, H., Chen, X., Cheng, Y., Wu, C., Dang, F., & Chen, X. (2022) · ACM Conference on Embedded Networked Sensor Systems (SenSys) · doi:10.1145/3560905.3568432 · Cited by 31
Islam, Q. U., Ibrahim, H., Chin, P. K., Lim, K., & Abdullah, M. Z. (2023) · Robotic Intelligence and Automation · doi:10.1108/ria-11-2022-0269 · Cited by 31
Loop Closure Detection Based on Multi-Scale Deep Feature Fusion
Chen, B., Yuan, D., Liu, C., & Wu, Q. H. (2019) · Applied Sciences · doi:10.3390/app9061120 · Cited by 31
Advanced Computing: An International Journal
Gaoussou, H., & Dewei, P. (2026) · Advanced Computing An International Journal · doi:10.5121/acij · Cited by 30
“There are lots of researches done on visual odometry that have been realized using monocular, stereo, and RGD-D sensors [5, 7, 8, 9, 11].”
InfluentialA Survey of Simultaneous Localization and Mapping with an Envision in 6G Wireless NetworksPreprint
Huang, B., Zhao, J., & Liu, J. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1909.05214 · Cited by 31
I2D-Loc: Camera localization via image to LiDAR depth flow
Chen, K., Yu, H., Yang, W. T., Yu, L., Scherer, S., & Xia, G.-S. (2022) · ISPRS Journal of Photogrammetry and Remote Sensing · doi:10.1016/j.isprsjprs.2022.10.009 · Cited by 32
3D reconstruction from endoscopy images: A survey
Yang, Z., Dai, J. P., & Pan, J. (2024) · Computers in Biology and Medicine · doi:10.1016/j.compbiomed.2024.108546 · Cited by 35
Semantic visual SLAM in populated environments
Riazuelo, L., Montano, L., & Montiel, J. M. M. (2017) · European Conference on Mobile Robots · doi:10.1109/ecmr.2017.8098697 · Cited by 29
“This is still the basis of state-of-the-art VSLAM systems also monocular [3] or RGB-D C2TAM [2] or ORBSLAM2 [27].”
BackgroundMethodInfluentialEfficient Map Compression for Collaborative Visual SLAM
Opdenbosch, D. V., Aykut, T., Alt, N., & Steinbach, E. G. (2018) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv.2018.00114 · Cited by 30
“For the evaluation, we utilized ORB-SLAM2 [22] in stereo mode on the well-known EuRoC micro aerial vehicle dataset [3].”
BackgroundMethodCORB-SLAM: A Collaborative Visual SLAM System for Multiple Robots
Li, F., Yang, S., Yi, X., & Yang, X. (2018) · Lecture notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering · doi:10.1007/978-3-030-00916-8_45 · Cited by 30
Jacobson, A., Zeng, F., Smith, D., Boswell, N., Peynot, T., & Milford, M. J. (2018) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2018.8593750 · Cited by 30
“We also present a comparison of our Semi-Supervised SLAM approach to a state-of-the-art metric SLAM system, ORB-SLAM2 [6], and compare our localization system to a state-of-the-art deep learning place recognition approach [5].”
BackgroundResultInfluentialSoria, P. R., Arrue, B. C., & Ollero, A. (2019) · IEEE Robotics & Automation Magazine · doi:10.1109/mra.2018.2884744 · Cited by 30
“Additionally, a camera is attached to the docking tool to compare the results with a monocular vision system (ORB_ SLAM2 [13]).”
MethodProbabilistic Permutation Synchronization Using the Riemannian Structure of the Birkhoff Polytope
Birdal, T., & Şimşekli, U. (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.2019.01136 · Cited by 28
“Correspondences fuel a large variety of computer vision applications such as structure-from-motion (SfM) [73], SLAM [61], 3D reconstruction [24, 10, 8], camera re-localization [71], image retrieval [52] and 3D scan stitching [45, 26].”
BackgroundVITAMIN-E: VIsual Tracking and MappINg With Extremely Dense Feature Points
Yokozuka, M., Oishi, S., Thompson, S., & Banno, A. (2019) · Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2019.00987 · Cited by 27
“State-of-the-art monocular SLAM methods, such as ORB-SLAM[21] and DSO[6], solve Equation 7 by decomposing it using the Schur complement matrix instead of directly solving it: where The decomposition allows us to solve bundle adjustment faster.”
BackgroundMethodInfluentialSemiautomatic Labeling for Deep Learning in Robotics
Gregorio, D. D., Tonioni, A., Palli, G., & Stefano, L. D. (2019) · IEEE Transactions on Automation Science and Engineering · doi:10.1109/tase.2019.2938316 · Cited by 30
“F can be obtained using any method to track the camera movement, for example, a motion capture system, a SLAM-based method like [22], or a camera mounted on a robotic arm in an eye-on-hand configuration.”
BackgroundMethodInfluentialBenchmark of Visual SLAM Algorithms: ORB-SLAM2 vs RTAB-Map
Ragot, N., Khemmar, R., Pokala, A., Rossi, R., & Ertaud, J.-Y. (2019) · International Conference on Emerging Security Technologies · doi:10.1109/est.2019.8806213 · Cited by 30
Persistent Stereo Visual Localization on Cross-Modal Invariant Map
Ding, X., Wang, Y., Xiong, R., Li, D., Tang, L., Yin, H., & Zhao, L. (2019) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2019.2942760 · Cited by 29
“We implement our method on top of the public ORB-SLAM system [53] with the loop closing module deactivated.”
Method3D Reconstruction system for collaborative scanning based on multiple RGB-D cameras
Xu, H., Hou, J., Yu, L., & Fei, S. (2019) · Pattern Recognition Letters · doi:10.1016/j.patrec.2019.10.020 · Cited by 30
EVA: EVAluating at-home rehabilitation exercises using augmented reality and low-cost sensors
Escalona, F., Martínez-Martín, E., Cruz, E., Cazorla, M., & Gomez‐Donoso, F. (2019) · Virtual Reality · doi:10.1007/s10055-019-00419-4 · Cited by 30
DeepCrashTest: Turning Dashcam Videos into Virtual Crash Tests for Automated Driving Systems
Bashetty, S. K., Amor, H. B., & Fainekos, G. (2020) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra40945.2020.9197053 · Cited by 31
“We evaluated several methods like DSO [48], LSD-SLAM [49], ORBSLAM [50] and even Deep learning based approaches like Deep-VO [51].”
MethodLee, D., Yu, H. W., Kim, S., Yoon, J. S., Lee, K., Chai, Y. J., Choi, J. Y., Kong, H., Lee, K. E., Cho, H. S., et al. (2020) · Scientific Reports · doi:10.1038/s41598-020-65439-6 · Cited by 30
Cross-Descriptor Visual Localization and Mapping
Dusmanu, M., Mikšík, O., Schönberger, J. L., & Pollefeys, M. (2021) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.00600 · Cited by 30
“, ORB-SLAM [36, 37]), visual odometry (e.”
Transformer guided geometry model for flow-based unsupervised visual odometry
Li, X., Hou, Y., Wang, P., Gao, Z., Xu, M., & Li, W. (2021) · Neural Computing and Applications · doi:10.1007/s00521-020-05545-8 · Cited by 30
“ORB-SLAM2-Monocular suffers from the tracking failure due to some low texture frames, while for VINS-Fusion-Stereo which utilizes optical flow to track feature points, the strong light change cause the error as highlighted in Fig.”
BackgroundMethodInfluentialSelf-supervised Visual-LiDAR Odometry with Flip Consistency
Li, B., Hu, M. H., Wang, S., Wang, L., & Gong, X. (2021) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv48630.2021.00389 · Cited by 28
“The former [30, 17, 27] follows a standard pipeline including feature extraction and matching, motion estimation, and local/global optimization.”
MethodHu, H., Wang, H., Liu, Z., & Chen, W. (2021) · IEEE/CAA Journal of Automatica Sinica · doi:10.1109/jas.2021.1003907 · Cited by 32
“addressed most cases of loop closure detection in real-time visual SLAM [29], [30] without significant environmental changes.”
BackgroundInfluentialMBA-VO: Motion Blur Aware Visual Odometry
Liu, P., Zuo, X., Larsson, V., & Pollefeys, M. (2021) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.00550 · Cited by 30
“In this case, ORB-SLAM [22] simply discards the severe blurred images without affecting the accuracy of the remaining frames.”
InfluentialA Survey on Perspective-n-Point Problem
Pan, S., & Wang, X. (2021) · Chinese Control Conference (CCC) · doi:10.23919/ccc52363.2021.9549863 · Cited by 30
“In front-end visual odometer of visual SLAM system [1, 2] which uses cameras as the only or main sensor, feature-based methods first extract the corresponding feature points from the image, then perform feature matching on the two images (find out the same features in the two images), and finally use the matched featu…”
MethodYang, A., Cui, C., Bârsan, I. A., Urtasun, R., & Wang, S. (2021) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra48506.2021.9561481 · Cited by 31
“15 showcase the trajectories in all 25 validation sequences, comparing ORB-SLAM2 using only the stereo cameras to our full system using all 7 asynchronous cameras.”
InfluentialShin, U., Lee, K., Lee, S., & Kweon, I. S. (2021) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2021.3137895 · Cited by 32
Robotic Computing on FPGAs: Current Progress, Research Challenges, and Opportunities
Wan, Z., Lele, A. S., Yu, B., Liu, S., Wang, Y., Reddi, V. J., Hao, C., & Raychowdhury, A. (2022) · IEEE International Conference on Artificial Intelligence Circuits and Systems (AICAS) · doi:10.1109/aicas54282.2022.9869951 · Cited by 30
“Simultaneous localization and mapping (SLAM) is a commonly-used algorithm where the robot simultaneously constructs a map of the environment while localizing itself [13], and one principled mathematical approach to solving SLAM is maximum a posteriori estimation.”
MethodA4LidarTag: Depth-Based Fiducial Marker for Extrinsic Calibration of Solid-State Lidar and Camera
Xie, Y., Deng, L., Sun, T., Fu, Y., Li, J., Cui, X., Yin, H., Deng, S., Xiao, J., & Chen, B. (2022) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2022.3173033 · Cited by 30
Visual-Inertial Odometry Using High Flying Altitude Drone Datasets
George, A., Koivumäki, N., Hakala, T., Suomalainen, J. M., & Honkavaara, E. (2023) · Drones · doi:10.3390/drones7010036 · Cited by 30
Lin, Y.-K., Lin, W., & Wang, C. (2023) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra48891.2023.10161269 · Cited by 30
“In most odometry approaches, the keyframe selection mechanism is widely used for computational efficiency [10]– [12].”
Method[POSTER] A Benchmark Dataset for 6DoF Object Pose Tracking
Wu, P.-C., Lee, Y.-Y., Tseng, H.-Y., Ho, H.-I., Yang, M.-H., & Chien, S.-Y. (2017) · 2017 IEEE International Symposium on Mixed and Augmented Reality (ISMAR-Adjunct) · doi:10.1109/ismar-adjunct.2017.62 · Cited by 35
“Two state-of-the-art approaches in this field, i.e., ORB-SLAM2 [14] and ElasticFusion [22], are used for evaluation.”
MethodInfluentialGPS-SLAM: An Augmentation of the ORB-SLAM Algorithm
Kiss-Illés, D., Barrado, C., & Salamí, E. (2019) · Sensors · doi:10.3390/s19224973 · Cited by 30
“ORB-SLAM is a very well-functioning SLAM algorithm written by Raúl Mur-Artal et al. [1,2].”
BackgroundMethodInfluentialTian, Y., Khosoussi, K., & How, J. P. (2020) · The International Journal of Robotics Research · doi:10.1177/0278364920948594 · Cited by 30
“, (Mur-Artal and Tardós 2017).”
MethodInfluentialTani, S., Ruscio, F., Bresciani, M., Nordfeldt-Fiol, B. M., Bonin‐Font, F., & Costanzi, R. (2023) · Ocean Engineering · doi:10.1016/j.oceaneng.2023.114757 · Cited by 29
LEAP-VO: Long-term Effective Any Point Tracking for Visual Odometry
Chen, W., Chen, L., Wang, R., & Pollefeys, M. (2024) · 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/cvpr52733.2024.01876 · Cited by 32
“Traditional feature-based methods like ORB-SLAM2 [22] and DynaSLAM[1] some-times fail to track camera movements in highly dynamic sequences, primarily due to outliers from dynamic object correspondences and segmentation-based only dynamic track estimation.”
MethodInfluentialNID-SLAM: Neural Implicit Representation-based RGB-D SLAM In Dynamic Environments
Xu, Z., Niu, J., Li, Q., Ren, T., & Chen, C. (2024) · IEEE International Conference on Multimedia and Expo (ICME) · doi:10.1109/icme57554.2024.10687512 · Cited by 35
“Visual SLAM algorithms utilize data collected by sensors, e.g., monocular, stereo and RGB-D cameras, to estimate the camera pose in previously unknown environments and incrementally build maps of the surrounding scenes [1].”
MethodPeng, C., Wang, Z., Liao, H., Li, T., Wu, X., & Zhang, Q. (2024) · Measurement · doi:10.1016/j.measurement.2024.116065 · Cited by 29
Wang, K., Guo, J. H., Chen, K., & Lǚ, J. (2025) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2025.3545479 · Cited by 29
Multi-View Fusion-Based 3D Object Detection for Robot Indoor Scene Perception
Wang, L., Li, R., Sun, J., Liu, X., Zhao, L., Seah, H. S., Quah, C. K., & Tandianus, B. (2019) · Sensors · doi:10.3390/s19194092 · Cited by 29
“We to extract For C n world , and then obtain the object point cloud P in the world coordinate system (for convenience, if we do not declare the coordinate system, it is in the world one):”
MethodA Robust Localization System for Inspection Robots in Sewer Networks
Alejo, D., Caballero, F., & Merino, L. (2019) · Sensors · doi:10.3390/s19224946 · Cited by 30
“We also compare the performance of our proposed localization method with two popular state of the art SLAM approaches: gmapping [51] and ORBSLAM-2 [15].”
BackgroundMethodResultRelocalization With Submaps: Multi-Session Mapping for Planetary Rovers Equipped With Stereo Cameras
Giubilato, R., Vayugundla, M., Schuster, M. J., Stürzl, W., Wedler, A., Triebel, R., & Debei, S. (2020) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2020.2964157 · Cited by 28
“such as ORB-SLAM2 [13] or LDSO [14], rely on bag of binary words [7] in conjunction with the ORB descriptor.”
MethodBroadcast Your Weaknesses: Cooperative Active Pose-Graph SLAM for Multiple Robots
Chen, Y., Zhao, L., Lee, K. M. B., Yoo, C., Huang, S., & Fitch, R. (2020) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2020.2970665 · Cited by 28
“Δt = 1 s, and the noise parameters to ̃ δ−2 ij = 10 (6), κ̃ij = 10(5), δ−2 ij = 10 (5)Nv and κij = 500Nv , where Nv is the number of common features visible in both Pi and Pj , similar to [18], [33].”
BackgroundMethodMannequinChallenge: Learning the Depths of Moving People by Watching Frozen People
Li, Z., Dekel, T., Cole, F. H., Tucker, R. P., Snavely, N., Liu, C., & Freeman, W. T. (2020) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2020.2974454 · Cited by 29
Visual SLAM With Drift-Free Rotation Estimation in Manhattan World
Liu, J., & Meng, Z.-Y. (2020) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2020.3014648 · Cited by 30
“ORB-SLAM2 [2] and the typical BA-based VO are tested for comparation.”
BackgroundMethodInfluentialSelf-Supervised Scale Recovery for Monocular Depth and Egomotion Estimation
Wagstaff, B., & Kelly, J. W. (2021) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros51168.2021.9635938 · Cited by 33
“Indeed, popular systems such as ORB-SLAM2 [10] are prone to scale drift.”
BackgroundInfluentialProject to Adapt: Domain Adaptation for Depth Completion from Noisy and Sparse Sensor Data
Lopez-Rodriguez, A., Busam, B., & Mikolajczyk, K. (2021) · Lecture notes in computer science · doi:10.1007/978-3-030-69525-5_20 · Cited by 31
Szrek, J., Trybała, P., Góralczyk, M., Michalak, A., Ziętek, B., & Zimroz, R. (2020) · Sensors · doi:10.3390/s21010141 · Cited by 29
“VO algorithms often allow input of supplementary data, such as odometry [58] or IMU [3,54,58] to improve positioning accuracy and reliability.”
BackgroundDevelopment of Augmented Reality System for Productivity Enhancement in Offshore Plant Construction
Choi, S.-I., & Park, J.-S. (2021) · Journal of Marine Science and Engineering · doi:10.3390/jmse9020209 · Cited by 29
An Analytical Solution to the IMU Initialization Problem for Visual-Inertial Systems
Zuñiga-Noël, D., Moreno, F.-Á., & González-Jiménez, J. (2021) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2021.3091407 · Cited by 29
Zhang, K., Liu, H., Fan, Z., Chen, X., Leng, Y., de Silva, C. W., & Fu, C. (2021) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2021.3062003 · Cited by 29
“In a previous study [21], the cumulative error of RGBD ORB-SLAM for estimating a straight trajectory was about 2%.”
BackgroundMethodInfluentialImproved Real-Time Monocular SLAM Using Semantic Segmentation on Selective Frames
Lee, J., Back, M., Hwang, S., & Chun, I. (2021) · IEEE transactions on intelligent transportation systems (Print) · doi:10.1109/tits.2022.3228525 · Cited by 29
“variations of ORB-SLAM2 [30]: 1) monocular setup without loop closing (LC), 2) monocular setup with LC, 3) stereo”
BackgroundInfluentialSelf-supervised Geometric Perception
Yang, H., Dong, W., Carlone, L., & Koltun, V. (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/cvpr46437.2021.01412 · Cited by 28
“It is a fundamental class of problems in computer vision that has extensive applications in object detection and pose estimation [77, 86], motion estimation and 3D reconstruction [18, 25], simultaneous localization and mapping (SLAM) [13], structure from motion (SfM) [62], and virtual and augmented reality [44], to na…”
A V-SLAM Guided and Portable System for Photogrammetric Applications
Torresani, A., Menna, F., Battisti, R., & Fabio Remondino, A. (2021) · Remote Sensing · doi:10.3390/rs13122351 · Cited by 29
“The proposed prototype builds upon OPEN-V-SLAM [43], which is derived from ORB-SLAM2 [42].”
MethodDirect Near-Infrared-Depth Visual SLAM With Active Lighting
Kong, D., Zhang, Y., & Dai, W. (2021) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2021.3096741 · Cited by 29
A Collaborative Visual SLAM Framework for Service Robots
Ouyang, M., Shi, X., Wang, Y., Tian, Y., Shen, Y., Wang, D., Wang, P., & Cao, Z. (2021) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros51168.2021.9636798 · Cited by 29
“overlapped views, they are usually considered as one stereo camera setup, where frames from one camera are tracked and mapped, while frames from the other help triangulate the keypoints [12].”
BackgroundMethodElhashash, M., & Qin, R. (2022) · ISPRS Journal of Photogrammetry and Remote Sensing · doi:10.1016/j.isprsjprs.2022.03.018 · Cited by 30
Scene Reconstruction with Functional Objects for Robot Autonomy
Han, M., Zhang, Z., Jiao, Z., Xie, X., Zhu, Y., Zhu, S. C., & Liu, H. (2022) · International Journal of Computer Vision · doi:10.1007/s11263-022-01670-0 · Cited by 29
“We obtain accurate camera poses with a state-of-the-art feature-based SLAM system (Mur-Artal and Tardós, 2017) based on RGB-D streams.”
MethodZhang, T., Zhang, L., Chen, Y., & Zhou, Y. (2022) · IEEE Transactions on Image Processing · doi:10.1109/tip.2022.3213189 · Cited by 38
“In terms of the density of the constructed map, SLAM systems roughly fall into two categories, sparse ones [7]– [10] and dense ones [11]–[13].”
DELTAR: Depth Estimation from a Light-Weight ToF Sensor and RGB Image
Li, Y., Liu, X., Dong, W., Zhou, H., Bao, H., Zhang, G., Zhang, Y., & Cui, Z. (2022) · Lecture notes in computer science · doi:10.1007/978-3-031-19769-7_36 · Cited by 29
Chen, L., Ling, Z., Gao, Y., Sun, R., & Jin, S. (2023) · Complex & Intelligent Systems · doi:10.1007/s40747-023-01031-5 · Cited by 29
Light Beacon-Aided AUV Electromagnetic Localization for Landing on a Planar Docking Station
Lin, M., Lin, R., Li, D., & Yang, C. (2023) · IEEE Journal of Oceanic Engineering · doi:10.1109/joe.2023.3265767 · Cited by 29
“Visual navigation is widely used in the terrestrial scenarios and the localization frequency can be up to 20 Hz [16].”
BackgroundLiang, R., Yuan, J., Kuang, B., Liu, Q., & Guo, Z. (2023) · Measurement Science and Technology · doi:10.1088/1361-6501/acfb2d · Cited by 29
“Dyna SLAM [13] CFP-SLAM [9] Blitz-SLAM [35] YOLO-SLAM [24] OPF-SLAM [36] PLD-SLAM [37] ORB-SLAM2 [5] 2,—indicates that the corresponding data were not provided in the original literature.”
ARDEA—An MAV with skills for future planetary missions
Lutz, P., Muller, M. G., Maier, M., Stoneman, S., Tomić, T., von Bargen, I., Schuster, M. J., Steidle, F., Wedler, A., Stürzl, W., et al. (2020) · Journal of Field Robotics · doi:10.1002/rob.21949 · Cited by 28
Wang, Z., Chen, H., Zhang, S., & Lou, Y. (2023) · IEEE/ASME Transactions on Mechatronics · doi:10.1109/tmech.2023.3272910 · Cited by 29
“However, outdoor environments, such as rough terrains and featureless water surface or ground, introduce difficultiesforcommonlyusedvSLAMalgorithms[3]toachieve robustperformance.”
BackgroundNgeljaratan, L. N., Baş, E. E., & Moustafa, M. A. (2024) · Sensors · doi:10.3390/s24051450 · Cited by 28
Fu, T., Su, S., Lu, Y., & Wang, C. (2024) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2024.3382533 · Cited by 30
“Most established SLAM systems [2], [3] are programmed in C++ for fast execution.”
BackgroundMethodDVI-SLAM: A Dual Visual Inertial SLAM Network
Peng, X., Liu, Z., Li, W., Tan, P., Cho, S. Y., & Wang, Q. (2024) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra57147.2024.10610042 · Cited by 28
Islam, Q. U., Khozaei, F., Barhoumi, E. M., Baig, I., & Ignatyev, D. (2024) · Robotics and Autonomous Systems · doi:10.1016/j.robot.2024.104871 · Cited by 28
Long, J., Wang, F., Liu, M., Wang, Y., & Zou, Q. (2025) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2025.3547101 · Cited by 29
“Although traditional Visual SLAM methods, such as ORB-SLAM2 [1], ORB-SLAM3 [2], and VINS-Mono [3], perform well in static environments, the presence of dynamic elements in real-world scenarios can lead to data association errors, affecting localization and mapping accuracy.”
Active Camera Relocalization from a Single Reference Image without Hand-Eye Calibration
Tian, F.-P., Feng, W., Zhang, Q., Wang, X., Sun, J., Loia, V., & Liu, Z. (2018) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2018.2870646 · Cited by 28
“Typical visual SLAM uses RGB images, including monocular SLAM [3], [4] and stereo SLAM [27], [28], or RGBD images [29] as input.”
MethodInfluentialChen, Y., Zhou, Y., Lv, Q., & Deveerasetty, K. K. (2018) · IEEE International Conference on Information and Automation (ICIA) · doi:10.1109/icinfa.2018.8812387 · Cited by 28
“Later, Mur-Artal [34] proposed the ORB-SLAM2 algorithm, which increase the support for stereo camera and RGB-D camera.”
MethodRetrieval-based Localization Based on Domain-invariant Feature Learning under Changing Environments
Hu, H., Wang, H., Liu, Z., Yang, C., Chen, W., & Xie, L. (2019) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros40897.2019.8968047 · Cited by 26
“These generally perform well on the famous real-time V-SLAM systems [18], but they fail if the query and database images are taken under tremendously different environments due to the mismatch of descriptors between them.”
BackgroundSTN-Homography: Direct Estimation of Homography Parameters for Image Pairs
Zhou, Q., & Li, X. S. (2019) · Applied Sciences · doi:10.3390/app9235187 · Cited by 28
Cheng, R., Wang, K., Lin, S., Hu, W., Yang, K., Huang, X. M., Li, H., Sun, D., & Bai, J. Y. (2019) · IEEE International Conference on Intelligent Transportation Systems (ITSC) · doi:10.1109/itsc.2019.8917508 · Cited by 28
“Aggregating local features (such as SURF [18] and ORB [19]) into compact vectors, BoW (bag of words) places a vital role in place recognition [20], [21], especially becomes a popular place recognition approaches in SLAM (simultaneous localization and mapping) system.”
BackgroundVisual Navigation Using a Webcam Based on Semantic Segmentation for Indoor Robots
Adachi, M., Shatari, S., & Miyamoto, R. (2019) · International Conference on Signal-Image Technology & Internet-Based Systems (SITIS) · doi:10.1109/sitis.2019.00015 · Cited by 28
“To reduce the cost of 3D sensors, some researchers have attempted to adopt 3D sensing based on multi-view stereo [11], [12].”
BackgroundLow-cost 3D scanning systems for cultural heritage documentation
Gautier, Q., Garrison, T. G., Rushton, F., Bouck, N., Lo, E., Tueller, P., Schurgers, C., & Kastner, R. (2020) · Journal of Cultural Heritage Management and Sustainable Development · doi:10.1108/jchmsd-03-2020-0032 · Cited by 28
Object Semantic Grid Mapping with 2D LiDAR and RGB-D Camera for Domestic Robot Navigation
Qi, X., Wang, W., Liao, Z., Zhang, X., Yang, D., & Wei, R. (2020) · Applied Sciences · doi:10.3390/app10175782 · Cited by 28
“Vision-based SLAM mainly builds feature maps, including points [15,16], lines [17,18], or planes [19,20].”
BackgroundDistributed Variable-Baseline Stereo SLAM from two UAVs
Karrer, M., & Chli, M. (2021) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra48506.2021.9560944 · Cited by 28
“Alongside the emergence of vision based SLAM for single robots [2], [16], [18], [22], research into multi-robot systems has been attracting increasing attention recently.”
Background∇SLAM: Dense SLAM meets Automatic Differentiation
Murthy, J. K., Iyer, G., & Paull, L. (2020) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra40945.2020.9197519 · Cited by 31
“be/2ygtSJTmo08 example, feature-based SLAM systems build a map of unique features (landmarks), including interest points [3], lines [4], planes [5], objects [6], etc.”
BackgroundDF-VO: What Should Be Learnt for Visual Odometry?
Zhan, H., Weerasekera, C. S., Bian, J.-W., Garg, R., & Reid, I. (2021) · arXiv · doi:10.48550/arxiv.2103.00933 · Cited by 31
“For KITTI Odometry criterion, ORB-SLAM2 shows less rotation drift r err but higher translation drift t err due to scale drift issue, which is also showed in Fig.”
InfluentialShao, X., Zhang, L., Zhang, T., Shen, Y., Li, H., & Zhou, Y. (2020) · Proceedings of the 28th ACM International Conference on Multimedia · doi:10.1145/3394171.3413867 · Cited by 23
“In [15], Mur-Artal and Tardos incorporated IMU measurement into the ORB-SLAM system [7, 13, 14, 16], which is widely used in the field of autonomous driving.”
MethodFC-SLAM: Federated Learning Enhanced Distributed Visual-LiDAR SLAM In Cloud Robotic System
Li, Z., Wang, L., Jiang, L., & Xu, C.-Z. (2019) · 2019 IEEE International Conference on Robotics and Biomimetics (ROBIO) · doi:10.1109/robio49542.2019.8961798 · Cited by 28
“State of the art studies include ORB-SLAM [15], etc.”
Background
Metadata
- Authors
- Mur-Artal, R., & Tardos, J. D.
- Affiliations
- Instituto de Investigación en Ingeniería de Aragón (ES)
- Venue
- IEEE Transactions on Robotics
- Published
- 2017-10
- Volume
- 33
- Issue
- 5
- Pages
- 1255-1262
- ISSN
- 1552-3098 (ISSN-L)
- 1941-0468
- OpenAlex
- W2535547924
- Cited by
- 6,898
- References
- 21
- Citations by year
- 2026: 521 · 2025: 851 · 2024: 944 · 2023: 962 · 2022: 910 · 2021: 870 · 2020: 754 · 2019: 636 · 2018: 360 · 2017: 90
- FWCI
- 463.87
- Type
- journal article
- Language
- en
- Open access
- green
- arxiv.org
- Locations
- IEEE Transactions on Robotics (publishedVersion)
- arXiv (Cornell University) (submittedVersion)
- arXiv (Cornell University)
- Funders
- Spanish government (DPI2015-67275)
- Aragón regional government (DGA T04-FSE)
- Ministerio de Educación Scholarship (FPU13/04175)
- 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 Vision and Imaging
- Keywords
- ORB-SLAM2, SLAM, monocular SLAM, stereo SLAM, RGB-D SLAM, loop closure, relocalization, bundle adjustment, visual odometry, trajectory estimation
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
