{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,29]],"date-time":"2026-09-29T18:02:10Z","timestamp":1790704930457,"version":"4.1.0"},"reference-count":56,"publisher":"Springer Science and Business Media LLC","issue":"13","license":[{"start":{"date-parts":[[2021,1,2]],"date-time":"2021-01-02T00:00:00Z","timestamp":1609545600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,1,2]],"date-time":"2021-01-02T00:00:00Z","timestamp":1609545600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"funder":[{"DOI":"10.13039\/501100010225","name":"National Outstanding Youth Foundation of China","doi-asserted-by":"publisher","award":["61906173"],"award-info":[{"award-number":["61906173"]}],"id":[{"id":"10.13039\/501100010225","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100014717","name":"National Outstanding Youth Science Fund Project of National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61822701"],"award-info":[{"award-number":["61822701"]}],"id":[{"id":"10.13039\/100014717","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Neural Comput & Applic"],"published-print":{"date-parts":[[2021,7]]},"DOI":"10.1007\/s00521-020-05545-8","type":"journal-article","created":{"date-parts":[[2021,1,2]],"date-time":"2021-01-02T03:02:53Z","timestamp":1609556573000},"page":"8031-8042","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":28,"title":["Transformer guided geometry model for flow-based unsupervised visual odometry"],"prefix":"10.1007","volume":"33","author":[{"given":"Xiangyu","family":"Li","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yonghong","family":"Hou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Pichao","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhimin","family":"Gao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mingliang","family":"Xu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wanqing","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2021,1,2]]},"reference":[{"key":"5545_CR1","unstructured":"Abadi M, Agarwal A, Barham P, Brevdo E, Chen Z, Citro C, Corrado GS, Davis A, Dean J, Devin M et al (2016) Tensorflow: Large-scale machine learning on heterogeneous distributed systems. arXiv:1603.04467"},{"key":"5545_CR2","doi-asserted-by":"crossref","unstructured":"Almalioglu Y, Saputra MRU, de\u00a0Gusmao PP, Markham A, Trigoni N (2019) Ganvo: unsupervised deep monocular visual odometry and depth estimation with generative adversarial networks. In: ICRA","DOI":"10.1109\/ICRA.2019.8793512"},{"issue":"4","key":"5545_CR3","doi-asserted-by":"publisher","first-page":"355","DOI":"10.1162\/pres.1997.6.4.355","volume":"6","author":"RT Azuma","year":"1997","unstructured":"Azuma RT (1997) A survey of augmented reality. Teleop Virtual Environ 6(4):355\u2013385","journal-title":"Teleop Virtual Environ"},{"key":"5545_CR4","unstructured":"Ba JL, Kiros JR, Hinton GE (2016) Layer normalization. arXiv preprint arXiv:1607.06450"},{"issue":"2","key":"5545_CR5","doi-asserted-by":"publisher","first-page":"207","DOI":"10.1177\/0278364913507326","volume":"33","author":"JL Blanco-Claraco","year":"2014","unstructured":"Blanco-Claraco JL, Moreno-Due\u00f1as F\u00c1, Gonz\u00e1lez-Jim\u00e9nez J (2014) The m\u00e1laga urban dataset: high-rate stereo and lidar in a realistic urban scenario. Int J Robot Res 33(2):207\u2013214","journal-title":"Int J Robot Res"},{"key":"5545_CR6","doi-asserted-by":"crossref","unstructured":"Chen C, Seff A, Kornhauser A, Xiao J (2015) Deepdriving: learning affordance for direct perception in autonomous driving. In: ICCV","DOI":"10.1109\/ICCV.2015.312"},{"key":"5545_CR7","doi-asserted-by":"crossref","unstructured":"Clark R, Wang S, Wen H, Markham A, Trigoni N (2017) Vinet: visual-inertial odometry as a sequence-to-sequence learning problem. In: AAAI","DOI":"10.1609\/aaai.v31i1.11215"},{"key":"5545_CR8","doi-asserted-by":"crossref","unstructured":"Costante G, Ciarfuglia TA (2018) LS-VO: learning dense optical subspace for robust visual odometry estimation. In: IEEE robotics and automation letters","DOI":"10.1109\/LRA.2018.2803211"},{"key":"5545_CR9","doi-asserted-by":"crossref","unstructured":"DeSouza GN, Kak AC (2002) Vision for mobile robot navigation: A survey. In: TPAMI","DOI":"10.1109\/34.982903"},{"key":"5545_CR10","doi-asserted-by":"publisher","first-page":"11217","DOI":"10.1007\/s00521-020-04702-3","volume":"32","author":"Y Ding","year":"2020","unstructured":"Ding Y, Lin L, Wang L, Zhang M, Li D (2020) Digging into the multiscale structure for a more refined depth map and 3d reconstruction. Neural Comput Appl 32:11217\u201311228","journal-title":"Neural Comput Appl"},{"issue":"2","key":"5545_CR11","doi-asserted-by":"publisher","first-page":"237","DOI":"10.1007\/s00521-009-0294-7","volume":"19","author":"Q Do","year":"2010","unstructured":"Do Q, Jain LC (2010) Application of neural processing paradigm in visual landmark recognition and autonomous robot navigation. Neural Comput Appl 19(2):237\u2013254","journal-title":"Neural Comput Appl"},{"key":"5545_CR12","doi-asserted-by":"crossref","unstructured":"Dosovitskiy A, Fischer P, Ilg E, Hausser P, Hazirbas C, Golkov V, Van Der\u00a0Smagt P, Cremers D, Brox T (2015) Flownet: learning optical flow with convolutional networks. In: ICCV","DOI":"10.1109\/ICCV.2015.316"},{"key":"5545_CR13","unstructured":"Eigen D, Puhrsch C, Fergus R (2014) Depth map prediction from a single image using a multi-scale deep network. In: Advances in neural information processing systems"},{"key":"5545_CR14","doi-asserted-by":"crossref","unstructured":"Engel J, Koltun V, Cremers D (2017) Direct sparse odometry. In: TPAMI","DOI":"10.1109\/TPAMI.2017.2658577"},{"key":"5545_CR15","doi-asserted-by":"crossref","unstructured":"Engel J, Sch\u00f6ps T, Cremers D (2014) LSD-SLAM: large-scale direct monocular slam. In: ECCV","DOI":"10.1007\/978-3-319-10605-2_54"},{"key":"5545_CR16","doi-asserted-by":"crossref","unstructured":"Geiger A, Lenz P, Urtasun R (2012) Are we ready for autonomous driving? the kitti vision benchmark suite. In: CVPR","DOI":"10.1109\/CVPR.2012.6248074"},{"key":"5545_CR17","doi-asserted-by":"crossref","unstructured":"Geiger A, Ziegler J, Stiller C (2011) Stereoscan: dense 3d reconstruction in real-time. In: IV","DOI":"10.1109\/IVS.2011.5940405"},{"key":"5545_CR18","doi-asserted-by":"crossref","unstructured":"Girdhar R, Carreira J, Doersch C, Zisserman A (2019) Video action transformer network. In: CVPR","DOI":"10.1109\/CVPR.2019.00033"},{"key":"5545_CR19","doi-asserted-by":"crossref","unstructured":"Godard C, Mac\u00a0Aodha O, Brostow GJ (2017) Unsupervised monocular depth estimation with left-right consistency. In: CVPR","DOI":"10.1109\/CVPR.2017.699"},{"key":"5545_CR20","doi-asserted-by":"crossref","unstructured":"He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition. In: CVPR","DOI":"10.1109\/CVPR.2016.90"},{"issue":"4","key":"5545_CR21","doi-asserted-by":"publisher","first-page":"1055","DOI":"10.1007\/s00521-016-2505-3","volume":"29","author":"C Hong","year":"2018","unstructured":"Hong C, Kiong L (2018) Topological Gaussian ARAM for biologically inspired topological map building. Neural Comput Appl 29(4):1055\u20131072","journal-title":"Neural Comput Appl"},{"key":"5545_CR22","unstructured":"Jaderberg M, Simonyan K, Zisserman A (2015) Spatial transformer networks. In: Advances in neural information processing systems"},{"key":"5545_CR23","doi-asserted-by":"crossref","unstructured":"Ji Y, Zhang H, Jie Z, Ma L, Wu, QJ (2020) Casnet: a cross-attention siamese network for video salient object detection. In: IEEE transactions on neural networks and learning systems","DOI":"10.1109\/TNNLS.2020.3007534"},{"key":"5545_CR24","doi-asserted-by":"crossref","unstructured":"Kendall A, Grimes M, Cipolla R (2015) Posenet: a convolutional network for real-time 6-dof camera relocalization. In: ICCV","DOI":"10.1109\/ICCV.2015.336"},{"key":"5545_CR25","doi-asserted-by":"crossref","unstructured":"Klein G. Murray D (2007) Parallel tracking and mapping for small ar workspaces. In: Proceedings of the 2007 6th IEEE and ACM International Symposium on Mixed and Augmented Reality, IEEE Computer Society, pp 1\u201310","DOI":"10.1109\/ISMAR.2007.4538852"},{"key":"5545_CR26","doi-asserted-by":"publisher","first-page":"15369","DOI":"10.1007\/s00521-019-04156-2","volume":"32","author":"J Li","year":"2020","unstructured":"Li J, Zhang Y, Chen Z, Wang J, Fang M, Luo C, Wang H (2020) A novel edgeenabled slam solution using projected depth image information. Neural Comput Appl 32:15369\u201315381","journal-title":"Neural Comput Appl"},{"key":"5545_CR27","doi-asserted-by":"crossref","unstructured":"Li R, Wang S, Long Z, Gu D (2018) Undeepvo: monocular visual odometry through unsupervised deep learning. In: ICRA","DOI":"10.1109\/ICRA.2018.8461251"},{"issue":"3","key":"5545_CR28","doi-asserted-by":"publisher","first-page":"1051","DOI":"10.1007\/s00521-012-1030-2","volume":"23","author":"S Li","year":"2013","unstructured":"Li S, Cui H, Li Y, Liu B, Lou Y (2013) Decentralized control of collaborative redundant manipulators with partial command coverage via locally connected recurrent neural networks. Neural Comput Appl 23(3):1051\u20131060","journal-title":"Neural Comput Appl"},{"key":"5545_CR29","doi-asserted-by":"publisher","first-page":"170","DOI":"10.1016\/j.neucom.2012.10.011","volume":"104","author":"Y Li","year":"2013","unstructured":"Li Y, Li S, Ge Y (2013) A biologically inspired solution to simultaneous localization and consistent mapping in dynamic environments. Neurocomputing 104:170\u2013179","journal-title":"Neurocomputing"},{"key":"5545_CR30","doi-asserted-by":"crossref","unstructured":"Li Y, Ushiku Y, Harada T (2019) Pose graph optimization for unsupervised monocular visual odometry. In: ICRA","DOI":"10.1109\/ICRA.2019.8793706"},{"issue":"6","key":"5545_CR31","doi-asserted-by":"publisher","first-page":"215","DOI":"10.1007\/s00521-016-2536-9","volume":"29","author":"Y Li","year":"2018","unstructured":"Li Y, Zhang J, Li S (2018) Stmvo: biologically inspired monocular visual odometry. Neural Comput Appl 29(6):215\u2013225","journal-title":"Neural Comput Appl"},{"key":"5545_CR32","doi-asserted-by":"crossref","unstructured":"Mahjourian R, Wicke M, Angelova A (2018) Unsupervised learning of depth and ego-motion from monocular video using 3d geometric constraints. In: CVPR","DOI":"10.1109\/CVPR.2018.00594"},{"key":"5545_CR33","doi-asserted-by":"crossref","unstructured":"Mayer N, Ilg E, Hausser P, Fischer P, Cremers D, Dosovitskiy A, Brox T (2016) A large dataset to train convolutional networks for disparity, optical flow, and scene flow estimation. In: CVPR","DOI":"10.1109\/CVPR.2016.438"},{"key":"5545_CR34","doi-asserted-by":"crossref","unstructured":"Menze M, Geiger A (2015) Object scene flow for autonomous vehicles. In: CVPR","DOI":"10.1109\/CVPR.2015.7298925"},{"issue":"4","key":"5545_CR35","doi-asserted-by":"publisher","first-page":"1065","DOI":"10.1007\/s00521-016-2717-6","volume":"30","author":"M Mitic","year":"2018","unstructured":"Mitic M, Vukovic N, Petrovic M, Miljkovic Z (2018) Chaotic metaheuristic algorithms for learning and reproduction of robot motion trajectories. Neural Comput Appl 30(4):1065\u20131083","journal-title":"Neural Comput Appl"},{"key":"5545_CR36","doi-asserted-by":"crossref","unstructured":"Mur-Artal R, Tard\u00f3s JD (2017) ORB-SLAM2: an open-source slam system for monocular, stereo, and RGB-D cameras. In: IEEE Transactions on Robotics","DOI":"10.1109\/TRO.2017.2705103"},{"key":"5545_CR37","unstructured":"Parmar N, Vaswani A, Uszkoreit J, Kaiser \u0141, Shazeer N, Ku A, Tran D (2018) Image transformer. arXiv preprint arXiv:1802.05751"},{"key":"5545_CR38","doi-asserted-by":"crossref","unstructured":"Pilzer A, Lathuiliere S, Sebe N, Ricci E (2019) Refine and distill: exploiting cycle-inconsistency and knowledge distillation for unsupervised monocular depth estimation. In: CVPR","DOI":"10.1109\/CVPR.2019.01000"},{"key":"5545_CR39","unstructured":"Qin T, Pan J, Cao S, Shen S (2019) A general optimization-based framework for local odometry estimation with multiple sensors. arXiv preprint arXiv:1901.03638"},{"key":"5545_CR40","unstructured":"Roberts RJW (2014) Optical flow templates for mobile robot environment understanding. Ph.D. thesis, Georgia Institute of Technology"},{"key":"5545_CR41","doi-asserted-by":"crossref","unstructured":"Shen T, Luo Z, Zhou L, Deng H, Zhang R, Fang T, Quan L (2019) Beyond photometric loss for self-supervised ego-motion estimation. In: ICRA","DOI":"10.1109\/ICRA.2019.8793479"},{"key":"5545_CR42","doi-asserted-by":"crossref","unstructured":"Sun D, Yang X, Liu MY, Kautz J (2018) PWC-NET: CNNS for optical flow using pyramid, warping, and cost volume. In: CVPR","DOI":"10.1109\/CVPR.2018.00931"},{"key":"5545_CR43","doi-asserted-by":"crossref","unstructured":"Ummenhofer B, Zhou H, Uhrig J, Mayer N, Ilg E, Dosovitskiy A, Brox T (2017) Demon: depth and motion network for learning monocular stereo. In: CVPR","DOI":"10.1109\/CVPR.2017.596"},{"key":"5545_CR44","unstructured":"Vaswani A, Shazeer N, Parmar N, Uszkoreit J, Jones L, Gomez AN, Kaiser \u0141, Polosukhin I (2017) Attention is all you need. In: Advances in neural information processing systems"},{"key":"5545_CR45","doi-asserted-by":"crossref","unstructured":"Wang R, Pizer SM, Frahm JM (2019) Recurrent neural network for (un-) supervised learning of monocular video visual odometry and depth. In: CVPR","DOI":"10.1109\/CVPR.2019.00570"},{"key":"5545_CR46","doi-asserted-by":"crossref","unstructured":"Wang S, Clark R, Wen H, Trigoni N (2017) Deepvo: Towards end-to-end visual odometry with deep recurrent convolutional neural networks. In: ICRA","DOI":"10.1109\/ICRA.2017.7989236"},{"issue":"4\u20135","key":"5545_CR47","doi-asserted-by":"publisher","first-page":"513","DOI":"10.1177\/0278364917734298","volume":"37","author":"S Wang","year":"2018","unstructured":"Wang S, Clark R, Wen H, Trigoni N (2018) End-to-end, sequence-to-sequence probabilistic visual odometry through deep neural networks. Int J Robot Res 37(4\u20135):513\u2013542","journal-title":"Int J Robot Res"},{"key":"5545_CR48","doi-asserted-by":"crossref","unstructured":"Wang Y, Wang P, Yang Z, Luo C, Yang Y, Xu W (2019) Unos: unified unsupervised optical-flow and stereo-depth estimation by watching videos. In: CVPR","DOI":"10.1109\/CVPR.2019.00826"},{"key":"5545_CR49","doi-asserted-by":"crossref","unstructured":"Wang Z, Bovik AC, Sheikh HR, Simoncelli EP (2004) Image quality assessment: from error visibility to structural similarity. In: TIP","DOI":"10.1109\/TIP.2003.819861"},{"key":"5545_CR50","doi-asserted-by":"crossref","unstructured":"Wong A, Soatto S (2019) Bilateral cyclic constraint and adaptive regularization for unsupervised monocular depth prediction. In: CVPR","DOI":"10.1109\/CVPR.2019.00579"},{"key":"5545_CR51","doi-asserted-by":"crossref","unstructured":"Xue F, Wang X, Li S, Wang Q, Wang J, Zha H (2019) Beyond tracking: selecting memory and refining poses for deep visual odometry. In: CVPR","DOI":"10.1109\/CVPR.2019.00877"},{"key":"5545_CR52","doi-asserted-by":"crossref","unstructured":"Yin Z, Shi J (2018) Geonet: unsupervised learning of dense depth, optical flow and camera pose. In: CVPR","DOI":"10.1109\/CVPR.2018.00212"},{"key":"5545_CR53","doi-asserted-by":"crossref","unstructured":"Zhan H, Garg R, Weerasekera CS, Li K, Agarwal H, Reid I (2018) Unsupervised learning of monocular depth estimation and visual odometry with deep feature reconstruction. In: CVPR","DOI":"10.1109\/CVPR.2018.00043"},{"key":"5545_CR54","doi-asserted-by":"crossref","unstructured":"Zhou H, Ummenhofer B, Brox T (2018) Deeptam: deep tracking and mapping. In: ECCV","DOI":"10.1007\/978-3-030-01270-0_50"},{"key":"5545_CR55","doi-asserted-by":"crossref","unstructured":"Zhou T, Brown M, Snavely N, Lowe DG (2017) Unsupervised learning of depth and ego-motion from video. In: CVPR","DOI":"10.1109\/CVPR.2017.700"},{"key":"5545_CR56","doi-asserted-by":"crossref","unstructured":"Zou Y, Luo Z, Huang JB (2018) Df-net: Unsupervised joint learning of depth and flow using cross-task consistency. In: ECCV","DOI":"10.1007\/978-3-030-01228-1_3"}],"container-title":["Neural Computing and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00521-020-05545-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00521-020-05545-8\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00521-020-05545-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,10]],"date-time":"2022-12-10T02:04:17Z","timestamp":1670637857000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00521-020-05545-8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,1,2]]},"references-count":56,"journal-issue":{"issue":"13","published-print":{"date-parts":[[2021,7]]}},"alternative-id":["5545"],"URL":"https:\/\/doi.org\/10.1007\/s00521-020-05545-8","relation":{},"ISSN":["0941-0643","1433-3058"],"issn-type":[{"value":"0941-0643","type":"print"},{"value":"1433-3058","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,1,2]]},"assertion":[{"value":"9 June 2020","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"18 November 2020","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"2 January 2021","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Compliance with ethical standards"}},{"value":"The authors declare that they have no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}