RD-VIO: Robust visual-inertial odometry for mobile augmented reality in dynamic environments
Open accessAbstract
It is typically challenging for visual or visual-inertial odometry systems to handle the problems of dynamic scenes and pure rotation. In this work, we design a novel visual-inertial odometry (VIO) system called RD-VIO to handle both of these two problems. First, we propose an IMU-PARSAC algorithm which can robustly detect and match keypoints in a two-stage process. In the first state, landmarks are matched with new keypoints using visual and IMU measurements. We collect statistical information from the matching and then guide the intra-keypoint matching in the second stage. Second, to handle the problem of pure rotation, we detect the motion type and adapt the deferred-triangulation technique during the data-association process. We make the pure-rotational frames into the special subframes. When solving the visual-inertial bundle adjustment, they provide additional constraints to the pure-rotational motion. We evaluate the proposed VIO system on public datasets and online comparison. Experiments show the proposed RD-VIO has obvious advantages over other methods in dynamic environments.
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
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?
RD-VIO incorporates radar data to leverage radar robustness under adverse weather for object tracking and localization.
“RD-VIO [6] takes this further by incorporating radar data, leveraging radar's robustness under adverse weather conditions to enhance object tracking and localization.”
From Multimodal fusion and vision–language models: A survey for robot vision (2026) · cites this paper as [6]
The paper describes RD-VIO as a visual-inertial system: its opening description (p. 1) says it matches landmarks using visual and IMU measurements, and the Introduction (p. 2) describes its handling of moving objects and pure rotation. It does not describe incorporating radar or using radar’s adverse-weather robustness; the claimed sensing method is contrary to the one the paper presents. (LLM, conf=0.90)
Checked by a reasoning model — may be wrong.
Experimental — accuracy not yet measuredMultimodal fusion combines complementary information from sensor inputs such as vision, language, depth, LiDAR, and tactile data, improving perception, reasoning, and decision-making in robot vision systems.
“In contrast, multimodal fusion integrates complementary information from various sensor inputs (e.g., vision, language, depth, LiDAR, and tactile data), thereby enhancing the perception, reasoning, and decision-making capabilities of robot vision systems [4,5,6,7].”
From Multimodal fusion and vision–language models: A survey for robot vision (2026) · cites this paper as [6]
The Introduction (p. 1) says fusing visual and inertial information improves robustness in complex environments, and §2.1 (p. 2) says that fusion helps recover metric scale. The paper does not support the broader examples of language, depth, LiDAR, or tactile inputs, or the claimed improvements in reasoning and decision-making. (LLM, conf=0.88)
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.
Cites
Fischler, M. A., & Bolles, R. C. (1981) · Communications of the ACM · doi:10.1145/358669.358692 · Cited by 25,893 · see citing works
Shi, J., & Tomasi (1994) · Proceedings of IEEE Conference on Computer Vision and Pattern Recognition CVPR-94 · doi:10.1109/cvpr.1994.323794 · Cited by 7,724 · cited 1× · see citing works
“3) Keypoint Tracking: We detect and track keypoints using KLT as described in [39].”
MethodORB-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 1× · see citing works
“Instead of choosing between two results, like in ORB-SLAM [28], we estimate the homography matrix after estimating the essential matrix.”
MethodORB-SLAM3: An Accurate Open-Source Library for Visual, Visual–Inertial, and Multimap SLAM
Campos, C., Elvira, R., Rodríguez, J. J. G., Montiel, J. M. M., & Tardos, J. D. (2021) · IEEE Transactions on Robotics · doi:10.1109/tro.2021.3075644 · Cited by 4,676 · cited 1× · see citing works
“In its recent evolution, ORB-SLAM3 [6] demonstrated a tightly-coupled system that produces astonishingly accurate results.”
BackgroundVINS-Mono: A Robust and Versatile Monocular Visual-Inertial State Estimator
Qin, T., Li, P., & Shen, S. (2018) · IEEE Transactions on Robotics · doi:10.1109/tro.2018.2853729 · Cited by 4,669 · cited 2× · see citing works
“We solve the following visual-inertial PnP to get an intial estimation to s i : arg min A typical sliding-window based system, like OKVIS [21] or VINS-Mono [34], will conditionally mark the new frame as a keyframe.”
Method(2020) · doi:10.1007/978-3-030-58536-5_24 · Cited by 2,824 · cited 1× · see citing works
“DROID-SLAM [43] uses a dense and accurate optical flow RAFT [42] as measurement, and builds an end-to-end network to perform bundle adjustment of pose and structure.”
MethodLeast-squares estimation of transformation parameters between two point patterns
Umeyama, S. (1991) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/34.88573 · Cited by 2,429 · cited 1× · see citing works
“This is done using the Umeyama algorithm [44].”
MethodThe 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× · see citing works
“(cid:2) The EuRoC [5] dataset is a benchmark dataset for VIO and SLAM algorithms.”
A Multi-State Constraint Kalman Filter for Vision-aided Inertial Navigation
Mourikis, A. I., & Roumeliotis, S. I. (2007) · Proceedings 2007 IEEE International Conference on Robotics and Automation · doi:10.1109/robot.2007.364024 · Cited by 1,951 · cited 1× · see citing works
“Filter-based VIO MSCKF [27] [24] are early VIO systems based on Kalman filtering.”
MethodOn-Manifold Preintegration for Real-Time Visual--Inertial Odometry
Forster, C., Carlone, L., Dellaert, F., & Scaramuzza, D. (2017) · IEEE Transactions on Robotics · doi:10.1109/tro.2016.2597321 · Cited by 1,502 · cited 1× · see citing works
“At the same time, we have q IMU , p IMU predicted by applying pre-integration from frame i − 1 to frame i .”
MethodDynaSLAM: Tracking, Mapping, and Inpainting in Dynamic Scenes
Bescos, B., Fácil, J. M., Civera, J., & Neira, J. (2018) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2018.2860039 · Cited by 1,333 · cited 3× · see citing works
“Both traditional methods, such as RDSLAM [41] based on the assumption of dynamic object distribution, and deep learning-based methods like Dy-naSLAM [3], DynaSLAM II [2], and DynaFusion [31], have conducted in-depth research on this issue.”
MethodDS-SLAM: A Semantic Visual SLAM towards Dynamic Environments
Yu, C., Liu, Z., Liu, X.-J., Xie, F., Yang, Y., Wei, Q., & Fei, Q. (2018) · 2018 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2018.8593691 · Cited by 1,154 · cited 2× · see citing works
“Thanks to the rapid development of deep learning, some systems such as Mask-SLAM [20], DS-SLAM [52], Dynamic-VINS [31], SOF-SLAM [10], Mask-Fusion [38] use semantic segmentations to aid moving object handling.”
MethodDynaSLAM: Tracking, Mapping and Inpainting in Dynamic Scenes
Bescos, B., Fácil, J. M., Civera, J., & Neira, J. (2018) · Zaguan (Universidad de Zaragoza) · Cited by 893 · see citing works
NICE-SLAM: Neural Implicit Scalable Encoding for SLAM
Zhu, Z., Peng, S., Larsson, V., Xu, W., Bao, H., Cui, Z., Oswald, M. R., & Pollefeys, M. (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/cvpr52688.2022.01245 · Cited by 865 · cited 1× · see citing works
“NICE-SLAM [53], Vox-Surf [22], Vox-Fusion [49] and the latest ESLAM [19], Co-SLAM [47] are typical neural implicit SLAM methods.”
MethodVisual-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× · see citing works
“VI-ORB-SLAM [29] is a loosely-coupled VI-SLAM system, meaning that its inertial measurements are not fused immediately with visual observations.”
BackgroundInverse Depth Parametrization for Monocular SLAM
Civera, J., Davison, A. J., & Montiel, J. M. M. (2008) · IEEE Transactions on Robotics · doi:10.1109/tro.2008.2003276 · Cited by 768 · cited 1× · see citing works
“In the initial phase, we align static 3D landmarks from the map to the 2D keypoints of the newly captured image.”
BackgroundOpenVINS: A Research Platform for Visual-Inertial Estimation
Geneva, P., Eckenhoff, K., Lee, W., Yang, Y., & Huang, G. P. (2020) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra40945.2020.9196524 · Cited by 711 · cited 1× · see citing works
“OpenVINS [14] is a newly open-source platform using MSCKF filter.”
MethodIterated extended Kalman filter based visual-inertial odometry using direct photometric feedback
Bloesch, M., Burri, M., Omari, S., Hutter, M., & Siegwart, R. (2017) · The International Journal of Robotics Research · doi:10.1177/0278364917728574 · Cited by 485 · cited 1× · see citing works
“ROVIO [4] is another filtering-based system that used photometric errors for visual observation.”
MethodKeyframe-Based Visual-Inertial SLAM using Nonlinear Optimization
Leutenegger, S., Furgale, P., Rabaud, V., Chli, M., Konolige, K., & Siegwart, R. (2013) · Robotics: Science and Systems · doi:10.15607/rss.2013.ix.037 · Cited by 480 · see citing works
A General Optimization-based Framework for Local Odometry Estimation with Multiple SensorsPreprint
Qin, T., Pan, J., Cao, S., & Shen, S.-J. (2019) · arXiv.org · doi:10.48550/arxiv.1901.03638 · Cited by 436 · cited 1× · see citing works
“VINS-Mono [34] and VINS-Fusion [35] [33] [34] are recent VI-SLAM systems.”
MaskFusion: Real-Time Recognition, Tracking and Reconstruction of Multiple Moving Objects
Rünz, M., Buffier, M., & Agapito, L. (2018) · Proceedings - International Symposium on Mixed and Augmented Reality, ISMAR · doi:10.1109/ismar.2018.00024 · Cited by 427 · cited 1× · see citing works
“Thanks to the rapid development of deep learning, some systems such as Mask-SLAM [20], DS-SLAM [52], Dynamic-VINS [31], SOF-SLAM [10], Mask-Fusion [38] use semantic segmentations to aid moving object handling.”
MethodDROID-SLAM: Deep Visual SLAM for Monocular, Stereo, and RGB-D CamerasPreprint
Teed, Z., & Deng, J. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2108.10869 · Cited by 360 · cited 1× · see citing works
“DROID-SLAM [43] uses a dense and accurate optical flow RAFT [42] as measurement, and builds an end-to-end network to perform bundle adjustment of pose and structure.”
MethodDynaSLAM II: Tightly-Coupled Multi-Object Tracking and SLAM
Bescos, B., Campos, C., Tardós, J. D., & Neira, J. (2021) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2021.3068640 · Cited by 343 · see citing works
PL-VIO: Tightly-Coupled Monocular Visual–Inertial Odometry Using Point and Line Features
He, Y., Zhao, J. Y., Guo, Y., He, W., & Yuan, K. (2018) · Sensors · doi:10.3390/s18041159 · Cited by 331 · cited 1× · see citing works
“PL-VINS [13] and PL-VIO [15] leverage a visual-inertial bundle adjustment to minimize separate reprojection errors for point features and line features in the visual measurement residuals.”
BackgroundAn Overview to Visual Odometry and Visual SLAM: Applications to Mobile Robotics
Yousif, K., Bab-Hadiashar, A., & Hoseinnezhad, R. (2015) · Intelligent Industrial Systems · doi:10.1007/s40903-015-0032-7 · Cited by 314 · cited 1× · see citing works
“[51] provides a useful review for visual-only SLAM systems.”
BackgroundRobust monocular SLAM in dynamic environments
Tan, W., Liu, H.-M., Dong, Z., Zhang, G., & Bao, H. (2013) · International Symposium on Mixed and Augmented Reality · doi:10.1109/ismar.2013.6671781 · Cited by 306 · see citing works
Co-SLAM: Joint Coordinate and Sparse Parametric Encodings for Neural Real-Time SLAM
Wang, H., Wang, J., & Agapito, L. (2023) · 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52729.2023.01277 · Cited by 287 · cited 1× · see citing works
“NICE-SLAM [53], Vox-Surf [22], Vox-Fusion [49] and the latest ESLAM [19], Co-SLAM [47] are typical neural implicit SLAM methods.”
MethodESLAM: Efficient Dense SLAM System Based on Hybrid Representation of Signed Distance Fields
Johari, M. M., Carta, C., & Fleuret, F. (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/cvpr52729.2023.01670 · Cited by 260 · cited 1× · see citing works
“NICE-SLAM [53], Vox-Surf [22], Vox-Fusion [49] and the latest ESLAM [19], Co-SLAM [47] are typical neural implicit SLAM methods.”
MethodDirect Sparse Visual-Inertial Odometry Using Dynamic Marginalization
Stumberg, L. V., Usenko, V., & Cremers, D. (2018) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2018.8462905 · Cited by 255 · cited 1× · see citing works
“VI-DSO [46] and DM-VIO [45] are VIO extensions of original DSO, which increase robustness and have true scale.”
BackgroundA General Optimization-based Framework for Global Pose Estimation with Multiple SensorsPreprint
Qin, T., Cao, S., Pan, J., et al. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1901.03642 · Cited by 253 · cited 1× · see citing works
“VINS-Mono [34] and VINS-Fusion [35] [33] [34] are recent VI-SLAM systems.”
Vox-Fusion: Dense Tracking and Mapping with Voxel-based Neural Implicit Representation
Yang, X., Li, H., Zhai, H., Ming, Y., Liu, Y., & Zhang, G. (2022) · Proceedings - International Symposium on Mixed and Augmented Reality, ISMAR · doi:10.1109/ismar55827.2022.00066 · Cited by 243 · cited 1× · see citing works
“NICE-SLAM [53], Vox-Surf [22], Vox-Fusion [49] and the latest ESLAM [19], Co-SLAM [47] are typical neural implicit SLAM methods.”
MethodImproving the accuracy of EKF-based visual-inertial odometry
Li, M., & Mourikis, A. I. (2012) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2012.6225229 · Cited by 194 · cited 1× · see citing works
“Filter-based VIO MSCKF [27] [24] are early VIO systems based on Kalman filtering.”
MethodRobocentric visual–inertial odometry
Huai, Z., & Huang, G. (2018) · IEEE/RJS International Conference on Intelligent RObots and Systems · doi:10.1177/0278364919853361 · Cited by 185 · cited 1× · see citing works
“R-VIO [17] is a novel robocentric VIO algorithm.”
MethodDM-VIO: Delayed Marginalization Visual-Inertial Odometry
von Stumberg, L., & Cremers, D. (2022) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2021.3140129 · Cited by 176 · cited 1× · see citing works
“VI-DSO [46] and DM-VIO [45] are VIO extensions of original DSO, which increase robustness and have true scale.”
BackgroundSOF-SLAM: A Semantic Visual SLAM for Dynamic Environments
Cui, L., & Ma, C. (2019) · IEEE Access · doi:10.1109/access.2019.2952161 · Cited by 165 · cited 1× · see citing works
“Thanks to the rapid development of deep learning, some systems such as Mask-SLAM [20], DS-SLAM [52], Dynamic-VINS [31], SOF-SLAM [10], Mask-Fusion [38] use semantic segmentations to aid moving object handling.”
MethodFoot-mounted inertial navigation made easy
Nilsson, J.-O., Gupta, A. K., & Händel, P. (2014) · International Conference on Indoor Positioning and Indoor Navigation · doi:10.1109/ipin.2014.7275464 · Cited by 161 · cited 1× · see citing works
“This technique is commonly known as the zero-velocity update (ZUPT) [30].”
MethodDynaVINS: A Visual-Inertial SLAM for Dynamic Environments
Song, S., Lim, H., Lee, A. J., & Myung, H. (2022) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2022.3203231 · Cited by 151 · cited 2× · see citing works
“DynaVINS [40] introduced a robust bundle adjustment capable of discarding dynamic outliers by utilizing pose priors derived from IMU preintegration.”
BackgroundMethodPL-VINS: Real-Time Monocular Visual-Inertial SLAM with Point and Line FeaturesPreprint
Fu, Q., Wang, J., Yu, H.-S., Ali, I., Guo, F., He, Y.-J., & Zhang, H. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2009.07462 · Cited by 145 · cited 1× · see citing works
“PL-VINS [13] and PL-VIO [15] leverage a visual-inertial bundle adjustment to minimize separate reprojection errors for point features and line features in the visual measurement residuals.”
BackgroundRobust initialization of monocular visual-inertial estimation on aerial robots
Qin, T., & Shen, S.-J. (2017) · IEEE/RJS International Conference on Intelligent RObots and Systems · doi:10.1109/iros.2017.8206284 · Cited by 138 · cited 1× · see citing works
“From the alignment, we can solve for gravity vector and the initial scale using the method introduced in [36].”
MethodSurvey and evaluation of monocular visual-inertial SLAM algorithms for augmented reality
Li, J., Yang, B.-B., Chen, D., Wang, N., Zhang, G., & Bao, H. (2019) · Virtual Reality & Intelligent Hardware · doi:10.1016/j.vrih.2019.07.002 · Cited by 128 · cited 1× · see citing works
“The experiment utilized the tracking accuracy and robustness [18] to evaluate the tracking quality of AR-based odometry and SLAM systems.”
MethodMonocular Visual-Inertial State Estimation for Mobile Augmented Reality
Li, P.-L., Qin, T., Hu, B., Zhu, F., & Shen, S.-J. (2017) · International Symposium on Mixed and Augmented Reality · doi:10.1109/ismar.2017.18 · Cited by 123 · cited 1× · see citing works
“1, the proposed VIO system RD-VIO can accommodate pure-rotational motions and large moving objects, which would easily lead to divergence on many other VIO/VI-SLAM systems, such as VINS-Mobile [25].”
BackgroundRGB-D Inertial Odometry for a Resource-Restricted Robot in Dynamic Environments
Liu, J., Li, X., Liu, Y., & Chen, H. (2022) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2022.3191193 · Cited by 110 · see citing works
Mask-SLAM: Robust Feature-Based Monocular SLAM by Masking Using Semantic Segmentation
Kaneko, M., Iwami, K., Ogawa, T., Yamasaki, T., & Aizawa, K. (2018) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw.2018.00063 · Cited by 104 · cited 1× · see citing works
“Thanks to the rapid development of deep learning, some systems such as Mask-SLAM [20], DS-SLAM [52], Dynamic-VINS [31], SOF-SLAM [10], Mask-Fusion [38] use semantic segmentations to aid moving object handling.”
MethodADVIO: An Authentic Dataset for Visual-Inertial Odometry
Cortés, S., Solin, A., Rahtu, E., & Kannala, J. (2018) · Lecture notes in computer science · doi:10.1007/978-3-030-01249-6_26 · Cited by 98 · see citing works
RNIN-VIO: Robust Neural Inertial Navigation Aided Visual-Inertial Odometry in Challenging Scenes
Chen, D., Wang, N., Xu, R.-S., Xie, W., Bao, H., & Zhang, G. (2021) · International Symposium on Mixed and Augmented Reality · doi:10.1109/ismar52148.2021.00043 · Cited by 75 · cited 1× · see citing works
“And some others like RNIN-VIO [7] take advantage of the neural network of IMU navigation to improve robustness.”
BackgroundVox-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 66 · cited 1× · see citing works
“NICE-SLAM [53], Vox-Surf [22], Vox-Fusion [49] and the latest ESLAM [19], Co-SLAM [47] are typical neural implicit SLAM methods.”
MethodDT-SLAM: Deferred Triangulation for Robust SLAM
Herrera, D., Kim, K., Kannala, J., Pulli, K., & Heikkilä, J. (2014) · International Conference on 3D Vision (3DV) · doi:10.1109/3dv.2014.49 · Cited by 59 · cited 2× · see citing works
“DT-SLAM [16] attempted to avoid triangulating new landmarks in order to prevent initialization with erroneous depths.”
BackgroundYe, W., Lan, X., Chen, S., Ming, Y., Yu, X., Bao, H., Cui, Z., & Zhang, G. (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/cvpr52729.2023.00924 · Cited by 51 · cited 1× · see citing works
“PVO [50] has a further performance improvement by coupling panoramic semantic segmentation.”
BackgroundHandling pure camera rotation in keyframe-based SLAM
Pirchheim, C., Schmalstieg, D., & Reitmayr, G. (2013) · Proceedings - International Symposium on Mixed and Augmented Reality, ISMAR · doi:10.1109/ismar.2013.6671783 · Cited by 47 · cited 1× · see citing works
“Another approach, described in[32], involves trackingrotation-onlycameras withpanoramas, resulting in a system with mixed geometry models.”
MethodLightweight hybrid visual-inertial odometry with closed-form zero velocity update
Xiaochen, Q. I. U., Zhang, H., & Fu, W. (2020) · Chinese Journal of Aeronautics · doi:10.1016/j.cja.2020.03.008 · Cited by 37 · cited 1× · see citing works
“LARVIO [48], a recent VIO system, employed the idea of ZUPT to improve performance.”
MethodRP-VIO: Robust Plane-based Visual-Inertial Odometry for Dynamic Environments
Ram, K., Kharyal, C., Harithas, S. S., & Krishna, K. M. (2021) · IEEE/RJS International Conference on Intelligent RObots and Systems · doi:10.1109/iros51168.2021.9636522 · Cited by 33 · cited 1× · see citing works
“In addition, some works rely on structure of planes like RP-VIO [37] and PVIO [23], that uses planar features to increase robustness and accuracy in dynamic environments.”
MethodRobust Tightly-Coupled Visual-Inertial Odometry with Pre-built Maps in High Latency Situations
Bao, H., Xie, W., Qian, Q., Chen, D., Zhai, S., Wang, N., & Zhang, G. (2022) · IEEE Transactions on Visualization and Computer Graphics · doi:10.1109/tvcg.2022.3150495 · Cited by 23 · cited 1× · see citing works
“In order to further improve the performance of VIO, some newly VIO systems like [1] use pre-built high-precision maps to improve accuracy greatly.”
MethodRobust and Efficient Visual-Inertial Odometry with Multi-plane Priors
Li, J., Yang, B., Huang, K., Zhang, G., & Bao, H. (2019) · Lecture notes in computer science · doi:10.1007/978-3-030-31726-3_24 · Cited by 13 · see citing works
Owada, S., & Fujiki, J. (2008) · International Symposium on Non-Photorealistic Animation and Rendering (NPAR) · doi:10.1145/1377980.1377994 · Cited by 11 · cited 3× · see citing works
“Both traditional methods, such as RDSLAM [41] based on the assumption of dynamic object distribution, and deep learning-based methods like Dy-naSLAM [3], DynaSLAM II [2], and DynaFusion [31], have conducted in-depth research on this issue.”
Method
Flagged first, then by citations
Cited by
Sorted by citations
Multimodal fusion and vision–language models: A survey for robot vision
Han, X., Chen, S., Fu, Z., Feng, Z., Fan, L., An, D., Wang, C., Guo, L., Meng, W., Zhang, X., et al. (2026) · Information Fusion · doi:10.1016/j.inffus.2025.103652 · Cited by 41 · see citing works
“RD-VIO [6] takes this further by incorporating radar data, leveraging radar’s robustness under adverse weather conditions to enhance object tracking and localization.”
InfluentialReview on SLAM algorithms for Augmented Reality
Sheng, X., Mao, S., Yan, Y., & Yang, X. (2024) · Displays · doi:10.1016/j.displa.2024.102806 · Cited by 41 · see citing works
Wu, W., Chen, C., Yang, B., Zou, X., Liang, F., Xu, Y., & He, X. (2025) · ISPRS Journal of Photogrammetry and Remote Sensing · doi:10.1016/j.isprsjprs.2025.01.036 · Cited by 34 · see citing works
PLE-SLAM: A Visual-Inertial SLAM Based on Point-Line Features and Efficient IMU Initialization
He, J., Li, M., Wang, Y., & Wang, H. (2025) · IEEE Sensors Journal · doi:10.1109/jsen.2024.3523039 · Cited by 23 · see citing works
“To further evaluate the localization accuracy on EuRoC dataset, we selected DM-VIO [44], RD-VIO [45], EPLF-VINS [13], ORB-SLAM3 [7], OKVIS2 [28], Dynam-SLAM [46], and MAVIS [47] for comparative experiments.”
R²-GVIO: A Robust, Real-Time GNSS-Visual-Inertial State Estimator in Urban Challenging Environments
Song, J., Li, W., Duan, C., & Zhu, X. (2024) · IEEE Internet of Things Journal · doi:10.1109/jiot.2024.3379755 · Cited by 26 · see citing works
“A similar strategy RD-VIO [22] is capable of handling pure-rotational movements and large moving objects.”
MethodLi, D., Shi, H., Bing, C., et al. (2025) · SmartBot · doi:10.1002/smb2.70000 · Cited by 21 · see citing works
Robust Collaborative Visual-Inertial SLAM for Mobile Augmented Reality
Pan, X., Huang, G., Zhang, Z., Li, J., Bao, H., & Zhang, G. (2024) · IEEE Transactions on Visualization and Computer Graphics · doi:10.1109/tvcg.2024.3456152 · Cited by 19 · see citing works
“The compared approaches include MSCKF [27] which are filter-based solutions, while OKVIS [20] and RD-VIO [21] are optimization-based VIO solutions.”
InfluentialDynaMoN: Motion-Aware Fast and Robust Camera Localization for Dynamic Neural Radiance Fields
Schischka, N., Schieber, H., Karaoglu, M. A., Görgülü, M., Grötzner, F., Ladikos, A., Navab, N., Roth, D., & Busam, B. (2024) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2024.3511399 · Cited by 13 · see citing works
“Although it performs well on large-scale datasets with up to over 4,000 images, handling scenes with close to 8,000 frames introduces significant challenges to the camera pose localization [51] and the NeRF [52].”
Liu, Y., Liu, L., Zheng, Y., Liu, Y., Dang, F., Li, N., & Ma, K. (2025) · Science China Information Sciences · doi:10.1007/s11432-024-4303-8 · Cited by 13 · see citing works
“In visual-inertial odometry [79, 80], ESVIO [81] introduces event-based stereo visual-inertial odometry, using event streams, standard images, and inertial measurements.”
Zhang, Q., Wang, S., Zhang, T., Ren, G., Zhang, L., Wang, Y., Zheng, B., Li, J., & Zheng, H. (2025) · Computers and Electronics in Agriculture · doi:10.1016/j.compag.2025.111227 · Cited by 16 · see citing works
Cheng, J., Gao, Y., Wang, H., et al. (2025) · Measurement · doi:10.1016/j.measurement.2025.116667 · Cited by 11 · see citing works
CMIF-VIO: A Novel Cross Modal Interaction Framework for Visual Inertial Odometry
Wang, Z., Zhang, Y., Xu, X., Xiong, M., Su, X., & Meng, F. (2024) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2024.3511374 · Cited by 10 · see citing works
“Therefore, VIO, as a low-cost and high-performance solution, has been developed and applied in the fields of mobile robot [5], [6], augmented reality [7], [8] and complex scenes [9], [10].”
Kakoutopoulos, K., Drakakis, E., Papadopoulou, A., & Goumopoulos, C. (2025) · Sensors · doi:10.3390/s25072081 · Cited by 9 · see citing works
“…device’s position by combining data from the camera and IMU and, while this approach enhances tracking accuracy under normal conditions, VIO systems remain sensitive to prolonged periods of no translational movement and to rotating the device without simultaneous forward or backward motion [60].”
Cao, L., Liu, J., Lei, J., et al. (2025) · Expert Systems with Applications · doi:10.1016/j.eswa.2025.126813 · Cited by 8 · see citing works
Wei, J., Song, M. H., & Yuan, Y. (2025) · Remote Sensing · doi:10.3390/rs17071136 · Cited by 6 · see citing works
DFF-VIO: A General Dynamic Feature Fused Monocular Visual-Inertial Odometry
Luo, N., Hu, Z., Ding, Y., Li, J., Zhao, H., Liu, G., & Wang, Q. (2024) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2024.3482573 · Cited by 5 · see citing works
“Currently, mainstream SLAM solutions for dynamic scenes [8], [9], [10] primarily focus on identifying and removing dynamic features to enhance the pose estimation.”
Illumination Robust Image Interval-Guided Adaptive Multifarious Hybrid Visual Inertial Odometry
Rong, L., Zhang, Y., Zhang, J., et al. (2025) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2025.3557096 · Cited by 5 · see citing works
“Second, the t d sequence, calibrated by the filtering for each frame in the interval, will be utilized to reacquire IMU data during the optimization phase, thus implementing a novel preintegration technique for the formulation of the inertial term in (33).”
Li, W., Wang, G., Zhang, Q., et al. (2025) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2025.3565096 · Cited by 4 · see citing works
“The outstanding performance of visual-inertial odometry (VIO) and visual-inertial navigation systems (VINS) has been demonstrated in unmanned aerial vehicles (UAVs) [3], [4] and consumer-grade augmented reality applications [5], [6].”
Review of augmented reality maintenance and registration in aerospace industry
Zhao, X. L., Liu, K., Fu, H., & Wang, Y. (2025) · Journal of Manufacturing Processes · doi:10.1016/j.jmapro.2025.07.063 · Cited by 3 · see citing works
Huo, Z., Jin, L., Sun, X., et al. (2025) · Measurement Science and Technology · doi:10.1088/1361-6501/ae06c3 · Cited by 3 · see citing works
“In order to address the aforementioned problem, existing research primarily focuses on two aspects: multi-sensor fusion [6, 7] and artificial intelligence assistance [8, 9].”
Voxel-SVIO: Stereo Visual-Inertial Odometry Based on Voxel Map
Yuan, Z., Lang, F., Deng, J., Luo, H., & Yang, X. Y. (2025) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2025.3568307 · Cited by 3 · see citing works
“We compare our Voxel-SVIO with five state-of-the-art VIO systems, i.e., DM-VIO [20], RD-VIO [11], VINs-Fusion [17], Open-VINs [7] and SchurVINs [5].”
DUAL-LIO: Dual-Inertia Aided Lightweight Legged Odometry Using Body Constraints
Wang, X., Wang, Y., Chi, J., et al. (2025) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2025.3614810 · Cited by 3 · see citing works
“Within the tested range of α ∈ [5 , 25], the drift rate remains within a narrow band of approximately ± 0.1, indicating that the model’s output is not highly sensitive to α .”
InfluentialSketch3DVE: Sketch-based 3D-Aware Scene Video Editing
Liu, F., Li, S.-Y., Cao, Y., Fu, H., & Gao, L. (2025) · ACM SIGGRAPH Conference (SIGGRAPH) · doi:10.1145/3721238.3730623 · Cited by 2 · see citing works
“3D scene editing methods [Li et al. 2024; Liu et al. 2024b; Mirzaei et al. 2023] modify 3D attributes to render edited videos, but struggle with structural modifications or produce rendering-style outputs.”
XR Reality Check: What Commercial Devices Deliver for Spatial Tracking
Hu, T., Du, T., Qu, Z., & Gorlatova, M. A. (2025) · Proceedings - International Symposium on Mixed and Augmented Reality, ISMAR · doi:10.1109/ismar67309.2025.00101 · Cited by 3 · see citing works
“This protocol was adopted because the AVP is the only XR device employing Optic ID (an iris-based authentication system) and featuring downward-facing tracking cameras, which could be obstructed if mounted on a 3D-printed head.”
Exploratory UAV Autonomous Visual Navigation With Spatiotemporal Cognition
Jia, H., He, H., Chao, E., & Zhang, B. (2025) · IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing · doi:10.1109/jstars.2025.3647148 · Cited by 2 · see citing works
“Specifically, UAVs utilize technologies such as the GPS [41] or visual odometry [42] to accurately estimate their pose, while collecting detailed information about surrounding obstacles through distance measurement sensors such as radar.”
A spatial cognition approach based on grid cell group representation for embodied intelligence
Chai, Q., Huang, G., Fei, Y., Ma, G., Zhang, G., & Tang, H. (2023) · Chinese Science Bulletin (Chinese Version) · doi:10.1360/tb-2023-0850 · Cited by 2 · see citing works
Monocular Visual-Inertial Odometry Based on Local Maximum A Posteriori Estimation
Ye, B., Gong, G., Li, N., et al. (2025) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2025.3528674 · Cited by 2 · see citing works
Rotation and Temporal Calibration of Event Camera and IMU Based on Contrast Maximization
Li, S., Li, X., Chen, S., & Zhou, Y. (2025) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2025.3568945 · Cited by 3 · see citing works
MUP-LIO: Mapping Uncertainty-aware Point-wise Lidar Inertial Odometry
Yao, H., Zhang, X., Sun, G. C., et al. (2024) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros58592.2024.10801762 · Cited by 1 · see citing works
“The Simultaneous Localization and Mapping (SLAM) system [1]–[5] is the core of many robot-related tasks, such as robotic exploration and inspection [6]–[9].”
Multiview Landmark-Assisted UAV Swarm 6-DoF Pose Estimation Using Resonant Beam and VIO
Du, S., Xu, M., Li, Y., et al. (2025) · IEEE Internet of Things Journal · doi:10.1109/jiot.2025.3573755 · Cited by 1 · see citing works
“…RD-VIO mitigates issues in dynamic environments and during pure rotational motion by introducing the inertial measurement unit (IMU) PARSAC algorithm for robust keypoint matching and using delayed triangulation to handle pure rotational frames, significantly reducing cumulative errors [14].”
PKL-VINS a robust monocular visual-inertial SLAM with point and keypoint-line features
Chen, Z., Liu, Z., Shen, H., et al. (2025) · Measurement Science and Technology · doi:10.1088/1361-6501/adeeb0 · Cited by 1 · see citing works
Shu, Z., Bei, S., Li, L., & Chen, Z. (2025) · IEEE Transactions on Visualization and Computer Graphics · doi:10.1109/tvcg.2025.3616838 · Cited by 3 · see citing works
“In conventional SLAM applications or handheld XR devices like smartphones, jitter has minimal impact on performance, so benchmarking typically focuses on absolute errors such as ATE [32,34,65].”
Pre-Dog-Leg: A Feature Optimization Method for Visual Inertial SLAM Based on Adaptive Preconditions
Zhao, J., Lv, S., Zhu, H., et al. (2025) · Sensors · doi:10.3390/s25196161 · Cited by 1 · see citing works
“[32] identifies pure rotation frames and designates them as special subframes in the backend BA, providing additional constraints.”
Map-Free Construction Robot Localization via BIM Point Clouds and improved 3D-NDT
Zeng, L., Cheng, S., Guo, S., et al. (2025) · IEEE Consumer Electronics Magazine · doi:10.1109/mce.2025.3633867 · Cited by 1 · see citing works
SS-VIO: A Novel Cross Modal State Space Visual Inertial Odometry
Qin, W., Lin, Z., Bai, L., Yao, S.-J., Xu, H., & Dong, X. (2025) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2025.3643327 · Cited by 1 · see citing works
VINS-Mah: A Robust Monocular Visual-Inertial State Estimator for Dynamic Environments
Hu, Y., & Gardi, A. (2026) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2026.3656724 · Cited by 1 · see citing works
“For quantitative evaluation, we compared our method with the baseline VINS-Mono [1], ORB-SLAM3 [3], and three SOTA approaches for dynamic environments: DynaVINS [12], DFF-VIO [13], and RD-VIO [14].”
Li, X., Huang, B., Jia, B., et al. (2026) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2026.3660896 · Cited by 1 · see citing works
“Successful implementations of SLAM, such as DM-VIO [35], PIPO-SLAM [6], RD-VIO [36], MCOV-SLAM [37], and Switch-SLAM [38], often rely on advanced marginalization techniques to balance computational demands and preserve e ff ective historical information.”
Understanding Sensor Vulnerabilities in Industrial XR Tracking
Saha, S., & Absur, M. N. (2026) · IEEE Conference on Virtual Reality and 3D User Interfaces Abstracts and Workshops (VRW) · doi:10.1109/vrw70859.2026.00165 · Cited by 1 · see citing works
“In parallel, robustness-focused VIO methods aim to improve performance in visually degraded or dynamic environments by mitigating outliers, handling degenerate motion, and imposing inertial constraints [14, 13].”
Augmented Reality Used in Technical Diagnostics and Maintenance
Janota, A., & Holečko, P. (2024) · doi:10.1109/elektro60337.2024.10557051 · Cited by 1 · see citing works
“The applications of AR are diverse, spanning numerous fields, including healthcare [4-5], medicine [6-8], education [9-11], retail shopping [12-13], the tourism industry [14-15], game development [16-17], promoting safety and security [18], development of mobile AR systems [19-20] and more.”
BackgroundAsıl, U., & Nasibov, E. N. (2024) · Research Square · doi:10.21203/rs.3.rs-4935014/v1
Han, J., Xiong, Z., Wang, J., et al. (2025) · Guidance Navigation and Control · doi:10.1142/s2737480725500219
Visual-inertial fusion SLAM system based on weighted mean filtering
Mai, X., Liu, S., Chen, H., et al. (2025) · Enterprise Information Systems · doi:10.1080/17517575.2025.2492788
“J. Li et al. (2024) designed a novel visual-inertial odometry (VIO) system called RD-VIO to handle the problems of dynamic scenes and pure rotation.”
Scalable Multi-Session Visual SLAM in Large-Scale Scenes with Subgraph Optimization
Pan, X., Li, Z., Fan, T., Zhai, H., Bao, H., & Zhang, G. (2025) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra55743.2025.11128582
“Existing methods have at-tracted considerable attention, spanning purely vision-based approaches [1], [2], [3], multi-sensor fusion techniques [4], [5], [6], and learning-based methods [7], [8], [9].”
Feng, Y., Xiang, J., Wang, Y., & Duan, C. (2025) · IEEE International Conference on Pattern Recognition and Machine Learning (PRML) · doi:10.1109/prml66062.2025.11159830
“We compared against three state-of-the-art approaches: - VINS-Fusion [19]: A tightly coupled visual-inertial SLAM system with fixed sensor weights.”
Id-Vio: an Illumination-Robust Visual-Inertial Odometry for Dynamic Scenarios
Wei, W., Tao, F., Liu, S., Liu, X., Li, J., Hu, Y., & Zhou, Y. (2025) · International Symposium on Intelligent Robotics and Systems (ISoIRS) · doi:10.1109/isoirs65690.2025.11167955
Du, S., Xu, M., Wen, F., et al. (2025) · IEEE Transactions on Vehicular Technology · doi:10.1109/tvt.2025.3628254
“VIO is well-suited for unknown environments, however, without external calibration, positioning errors may amplify over time due to the accumulation of sensor errors [5], [12].”
Real-Time Consistent Monocular Depth Recovery System for Dynamic Environments
Huang, G., Pan, X., Lin, H., Zhang, Z., Xu, W., & Zhang, G. (2025) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros60139.2025.11246257
“RD-VIO [31] enhances robustness in dynamic environments by introducing the IMU-PARSAC algorithm for reliable keypoint matching.”
DW-VIO: Deep Weighted Visual-Inertial Odometry
Chen, G., Guo, X., Pan, X., Shen, Y., Zhang, G., Bao, H., & Cui, Z. (2025) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros60139.2025.11246552
Han, B., Li, T., Lv, Y., et al. (2026) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2026.3673929
“V ISUAL-INERTIAL Odometry (VIO) and Simultaneous Localization and Mapping (SLAM) constitute the foundational perception layer for autonomous mobile robots [1], [2], [3], uncrewed aerial vehicles (UAVs) [4], [5], and augmented reality (AR) devices [6], [7].”
Change-Resilient Localization Estimation
Reyes‐Aviles, F., Fleck, P., Schmalstieg, D., & Arth, C. (2026) · IEEE Conference on Virtual Reality and 3D User Interfaces (VR) · doi:10.1109/vr67842.2026.00041
“Many methods [30,50,52,56] have been proposed to tackle real-world challenges such as changing environment geometries, lighting conditions, and camera or motion artifacts.”
基于目标跟踪和改进高斯混合模型的动态场景视觉惯性SLAM方法
Jinyan, 李. L., Genliang, 熊. X., Bowen, 党. D., Qirong, 汤. T., & Tian, 兰. L. (2026) · Laser & Optoelectronics Progress · doi:10.3788/lop251456
Optimization of 3D Reconstruction Algorithm for Virtual Reality Environment Based on Computer Vision
Li, S. (2025) · doi:10.1109/cnc68716.2025.11484676
“The fused features F fusion ∈ R H×W×C can be expressed as (2): Among them, F i represents the feature maps at different scales, and W i and b i are the weights and biases of each scale respectively [12].”
A sensor weights balancing strategy for GNSS-vision-IMU integration navigation
Cheng, Z. L., Liu, W., Duan, C., et al. (2026) · Measurement Science and Technology · doi:10.1088/1361-6501/ae7506
“More recently, robust visual-inertial odometry (VIO) systems have been proposed to handle challenging scenarios, such as RD-VIO for dynamic environments [16].”
Zhou, Y., Wang, X., Wang, X., et al. (2026) · Measurement Science and Technology · doi:10.1088/1361-6501/ae74f1
“Integrating a microelectromechanical-system (MEMS) inertial measurement unit (IMU) is a common and cost-effective strategy, but it typically relies on visual estimation to correct inertial drift [14].”
Visual Camera Localization by Globally Consistent Descriptor Learning and Combined Bundle Adjustment
Wang, J., Wang, Y., Wang, C., et al. (2026) · IEEE Transactions on Image Processing · doi:10.1109/tip.2026.3698365
“These experiments benchmark our approach against several state-of-the-art visual-inertial SLAM frameworks, including Vins-Mono [7], PLF-Vins [61], DynaVins [23], EPLF-Vins [63], DM-VIO [22] and RD-VIO [66].”
Zhang, J., Liu, Y., Hu, X., et al. (2026) · Measurement Science and Technology · doi:10.1088/1361-6501/ae799b
“In [20], the authors utilized visual and inertial measurement data to perform matching between landmarks and new keypoints, thereby enhancing the system’s estimation stability in dynamic scenes.”
Improving visual SLAM robustness in dynamic indoor environments through hybrid feature preservation
Li, J., Yu, J., Nguyen, T.-T., et al. (2026) · Discover Artificial Intelligence · doi:10.1007/s44163-026-01578-5
“RD-VIO, a relative-depth-aided visual-inertial odometry system improving global consistency through tight IMU coupling [17, 18].”
Event-Triggered Dual-Screening for Robust Visual-Inertial Odometry in Dynamic Environments
Gong, C., & Wang, Z. (2026) · Chinese Control and Decision Conference (CCDC) · doi:10.1109/ccdc69976.2026.11559817
“Motion prior-based methods use IMU data: RD-VIO [20] guides RANSAC sampling with IMU pre-integration.”
Adaptive Visual-Inertial Fusion for GNSS-Denied Environments Using Factor Graph Optimization
Shichen, Q., Xie, X., Wu, J. H., et al. (2026) · Chinese Control and Decision Conference (CCDC) · doi:10.1109/ccdc69976.2026.11560181
“Li et al. developed RD-VIO, which improves localization accuracy in dynamic scenes through two-stage keypoint processing and delayed rotation triangulation [12].”
WHF-VIO: Wave-Aware Height Factor for Robust Visual–Inertial Odometry of Unmanned Surface Vehicles
Shen, A., Yang, S., Kuang, R., et al. (2026) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2026.3726121
“…prior e ff orts explore several directions, including maintaining a compact feature budget for stable tracking [17], strengthening outlier resistance in data association [18], and using light detection and ranging (LiDAR)–inertial–visual fusion to provide complementary geometric constraints [19].”
苏永善, Qinghua, Z., Jin, Z., et al. (2026) · Journal of Physics Conference Series · doi:10.1088/1742-6596/3326/1/012015
- Authors
- Li, J., Pan, X., Huang, G., Zhang, Z., Wang, N., Bao, H., & Zhang, G.
- Affiliations
- Zhejiang University (CN)
- Sensetime (China) (CN)
- Venue
- IEEE Transactions on Visualization and Computer Graphics
- Published
- 2024-10
- Volume
- 30
- Issue
- 10
- Pages
- 6941-6955
- ISSN
- 1077-2626 (ISSN-L)
- 1941-0506
- 2160-9306
- OpenAlex
- W4390816654
- Semantic Scholar
- 4d0c4064912b23210107301802b46937ae5d5d33
- Cited by
- 62
- References
- 54
- Citations by year
- 2026: 16 · 2025: 36 · 2024: 9 · 2023: 1
- FWCI
- 10.54
- Type
- journal article
- Language
- en
- Open access
- green
- arxiv.org
- Licence
- Locations
- IEEE Transactions on Visualization and Computer Graphics (publishedVersion)
- PubMed (publishedVersion)
- arXiv (Cornell University) (submittedVersion)
- arXiv (Cornell University)
- Funders
- National Natural Science Foundation of China (61932003)
- Topics
- Physical Sciences › Engineering › Aerospace Engineering › Robotics and Sensor-Based Localization
- Physical Sciences › Engineering › Aerospace Engineering › Inertial Sensor and Navigation
- Physical Sciences › Earth and Planetary Sciences › Geology › 3D Surveying and Cultural Heritage
- Keywords
- visual-inertial odometry, mobile augmented reality, dynamic environments, pure rotation, feature point matching, data association
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
