{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,29]],"date-time":"2025-11-29T08:00:37Z","timestamp":1764403237344},"reference-count":74,"publisher":"Springer Science and Business Media LLC","issue":"7","license":[{"start":{"date-parts":[[2023,3,13]],"date-time":"2023-03-13T00:00:00Z","timestamp":1678665600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,3,13]],"date-time":"2023-03-13T00:00:00Z","timestamp":1678665600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Neural Process Lett"],"published-print":{"date-parts":[[2023,12]]},"DOI":"10.1007\/s11063-023-11224-1","type":"journal-article","created":{"date-parts":[[2023,3,26]],"date-time":"2023-03-26T22:39:44Z","timestamp":1679870384000},"page":"9743-9764","update-policy":"http:\/\/dx.doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["Eliminating Scale Ambiguity of Unsupervised Monocular Visual Odometry"],"prefix":"10.1007","volume":"55","author":[{"given":"Zhongyi","family":"Wang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mengjiao","family":"Shen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qijun","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,3,13]]},"reference":[{"key":"11224_CR1","first-page":"1","volume":"71","author":"J Yin","year":"2022","unstructured":"Yin J, Luo D, Yan F, Zhuang Y (2022) A novel lidar-assisted monocular visual slam framework for mobile robots in outdoor environments. IEEE Trans Instrum Meas 71:1\u201311","journal-title":"IEEE Trans Instrum Meas"},{"issue":"10","key":"11224_CR2","doi-asserted-by":"publisher","first-page":"2478","DOI":"10.1109\/TPAMI.2019.2909895","volume":"42","author":"EJ Shamwell","year":"2019","unstructured":"Shamwell EJ, Lindgren K, Leung S, Nothwang WD (2019) Unsupervised deep visual-inertial odometry with online error correction for rgb-d imagery. IEEE Trans Pattern Anal Mach Intell 42(10):2478\u20132493","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"issue":"7","key":"11224_CR3","doi-asserted-by":"publisher","first-page":"9089","DOI":"10.1109\/TITS.2021.3090675","volume":"23","author":"A Beauvisage","year":"2021","unstructured":"Beauvisage A, Ahiska K, Aouf N (2021) Robust multispectral visual-inertial navigation with visual odometry failure recovery. IEEE Trans Intell Transp Syst 23(7):9089\u20139101","journal-title":"IEEE Trans Intell Transp Syst"},{"key":"11224_CR4","doi-asserted-by":"publisher","first-page":"2820","DOI":"10.1109\/TMM.2020.3017886","volume":"23","author":"X Gong","year":"2020","unstructured":"Gong X, Liu Y, Wu Q, Huang J, Zong H, Wang J (2020) An accurate, robust visual odometry and detail-preserving reconstruction system. IEEE Trans Multimedia 23:2820\u20132832","journal-title":"IEEE Trans Multimedia"},{"issue":"4","key":"11224_CR5","doi-asserted-by":"crossref","first-page":"80","DOI":"10.1109\/MRA.2011.943233","volume":"18","author":"F Fraundorfer","year":"2011","unstructured":"Fraundorfer F, Scaramuzza D (2011) Visual odometry: Part i: The first 30 years and fundamentals. IEEE Robot Autom Mag 18(4):80\u201392","journal-title":"IEEE Robot Autom Mag"},{"issue":"6","key":"11224_CR6","doi-asserted-by":"publisher","first-page":"1309","DOI":"10.1109\/TRO.2016.2624754","volume":"32","author":"C Cadena","year":"2016","unstructured":"Cadena C, Carlone L, Carrillo H, Latif Y, Scaramuzza D, Neira J, Reid I, Leonard JJ (2016) Past, present, and future of simultaneous localization and mapping: Toward the robust-perception age. IEEE Trans Robot 32(6):1309\u20131332","journal-title":"IEEE Trans Robot"},{"issue":"2","key":"11224_CR7","first-page":"1","volume":"51","author":"MRU Saputra","year":"2018","unstructured":"Saputra MRU, Markham A, Trigoni N (2018) Visual slam and structure from motion in dynamic environments: a survey. ACM Comp Surv (CSUR) 51(2):1\u201336","journal-title":"ACM Comp Surv (CSUR)"},{"issue":"3","key":"11224_CR8","doi-asserted-by":"publisher","first-page":"729","DOI":"10.1007\/s12555-018-0130-x","volume":"17","author":"M Sualeh","year":"2019","unstructured":"Sualeh M, Kim G-W (2019) Simultaneous localization and mapping in the epoch of semantics: a survey. Int J Control Autom Syst 17(3):729\u2013742","journal-title":"Int J Control Autom Syst"},{"issue":"5","key":"11224_CR9","doi-asserted-by":"publisher","first-page":"1255","DOI":"10.1109\/TRO.2017.2705103","volume":"33","author":"R Mur-Artal","year":"2017","unstructured":"Mur-Artal R, Tard\u00f3s JD (2017) Orb-slam2: an open-source slam system for monocular, stereo, and rgb-d cameras. IEEE Trans Robot 33(5):1255\u20131262","journal-title":"IEEE Trans Robot"},{"key":"11224_CR10","unstructured":"Jakob\u00a0Engel DC Vladlen Koltun (2016) Direct sparse odometry. arXiv preprint arXiv:1607.02565"},{"key":"11224_CR11","doi-asserted-by":"crossref","unstructured":"Wang R, Schworer M, Cremers D (2017) Stereo dso: Large-scale direct sparse visual odometry with stereo cameras. In: 2017 IEEE international conference on computer vision (ICCV), pp. 3923\u20133931","DOI":"10.1109\/ICCV.2017.421"},{"issue":"4","key":"11224_CR12","doi-asserted-by":"publisher","first-page":"730","DOI":"10.1109\/TPAMI.2015.2469274","volume":"38","author":"S Song","year":"2015","unstructured":"Song S, Chandraker M, Guest CC (2015) High accuracy monocular sfm and scale correction for autonomous driving. IEEE Trans Pattern Anal Mach Intell 38(4):730\u2013743","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"11224_CR13","unstructured":"Bian J, Li Z, Wang N, Zhan H, Shen C, Cheng M-M, Reid I (2019) Unsupervised scale-consistent depth and ego-motion learning from monocular video. Adv Neural Inf Process Syst. 32"},{"issue":"8","key":"11224_CR14","doi-asserted-by":"publisher","first-page":"2988","DOI":"10.1109\/TIM.2018.2871228","volume":"68","author":"J Al Hage","year":"2018","unstructured":"Al Hage J, Mafrica S, El Najjar MEB, Ruffier F (2018) Informational framework for minimalistic visual odometry on outdoor robot. IEEE Trans Instrum Meas 68(8):2988\u20132995","journal-title":"IEEE Trans Instrum Meas"},{"issue":"8","key":"11224_CR15","doi-asserted-by":"publisher","first-page":"5875","DOI":"10.1109\/TIM.2020.2964066","volume":"69","author":"S Chiodini","year":"2020","unstructured":"Chiodini S, Giubilato R, Pertile M, Debei S (2020) Retrieving scale on monocular visual odometry using low-resolution range sensors. IEEE Trans Instrum Meas 69(8):5875\u20135889","journal-title":"IEEE Trans Instrum Meas"},{"issue":"11","key":"11224_CR16","doi-asserted-by":"publisher","first-page":"1829","DOI":"10.3390\/rs10111829","volume":"10","author":"T Yang","year":"2018","unstructured":"Yang T, Ren Q, Zhang F, Xie B, Ren H, Li J, Zhang Y (2018) Hybrid camera array-based uav auto-landing on moving ugv in gps-denied environment. Remote Sens 10(11):1829","journal-title":"Remote Sens"},{"issue":"8","key":"11224_CR17","doi-asserted-by":"publisher","first-page":"1563","DOI":"10.1109\/TCSVT.2015.2452781","volume":"26","author":"G Lentaris","year":"2015","unstructured":"Lentaris G, Stamoulias I, Soudris D, Lourakis M (2015) Hw\/sw codesign and fpga acceleration of visual odometry algorithms for rover navigation on mars. IEEE Trans Circuits Syst Video Technol 26(8):1563\u20131577","journal-title":"IEEE Trans Circuits Syst Video Technol"},{"key":"11224_CR18","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: 2017 IEEE international conference on robotics and automation (ICRA), pp. 2043\u20132050. IEEE","DOI":"10.1109\/ICRA.2017.7989236"},{"issue":"4\u20135","key":"11224_CR19","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 Rob Res 37(4\u20135):513\u2013542","journal-title":"Int J Rob Res"},{"key":"11224_CR20","doi-asserted-by":"crossref","unstructured":"Konda KR, Memisevic R (2015) Learning visual odometry with a convolutional network. In: VISAPP (1), pp 486\u2013490","DOI":"10.5220\/0005299304860490"},{"issue":"1","key":"11224_CR21","doi-asserted-by":"publisher","first-page":"18","DOI":"10.1109\/LRA.2015.2505717","volume":"1","author":"G Costante","year":"2015","unstructured":"Costante G, Mancini M, Valigi P, Ciarfuglia TA (2015) Exploring representation learning with cnns for frame-to-frame ego-motion estimation. IEEE Robot Autom Lett 1(1):18\u201325","journal-title":"IEEE Robot Autom Lett"},{"key":"11224_CR22","doi-asserted-by":"crossref","unstructured":"Saputra MRU, De\u00a0Gusmao PP, Wang S, Markham A, Trigoni N (2019) Learning monocular visual odometry through geometry-aware curriculum learning. In: 2019 international conference on robotics and automation (ICRA), pp 3549\u20133555. IEEE","DOI":"10.1109\/ICRA.2019.8793581"},{"key":"11224_CR23","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: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 8575\u20138583","DOI":"10.1109\/CVPR.2019.00877"},{"key":"11224_CR24","doi-asserted-by":"crossref","unstructured":"Saputra MRU, De\u00a0Gusmao PP, Almalioglu Y, Markham A, Trigoni N (2019) Distilling knowledge from a deep pose regressor network. In: Proceedings of the IEEE\/CVF international conference on computer vision, pp 263\u2013272","DOI":"10.1109\/ICCV.2019.00035"},{"issue":"1","key":"11224_CR25","doi-asserted-by":"publisher","first-page":"308","DOI":"10.1109\/TITS.2020.3010418","volume":"23","author":"G Wang","year":"2020","unstructured":"Wang G, Zhang C, Wang H, Wang J, Wang Y, Wang X (2020) Unsupervised learning of depth, optical flow and pose with occlusion from 3d geometry. IEEE Trans Intell Transp Syst 23(1):308\u2013320","journal-title":"IEEE Trans Intell Transp Syst"},{"key":"11224_CR26","doi-asserted-by":"crossref","unstructured":"Jiang S, Campbell D, Liu M, Gould S, Hartley R (2020) Joint unsupervised learning of optical flow and egomotion with bi-level optimization. In: 2020 international conference on 3D vision (3DV), pp 682\u2013691. IEEE","DOI":"10.1109\/3DV50981.2020.00078"},{"issue":"10","key":"11224_CR27","doi-asserted-by":"publisher","first-page":"2624","DOI":"10.1109\/TPAMI.2019.2930258","volume":"42","author":"C Luo","year":"2019","unstructured":"Luo C, Yang Z, Wang P, Wang Y, Xu W, Nevatia R, Yuille A (2019) Every pixel counts++: joint learning of geometry and motion with 3d holistic understanding. IEEE Trans Pattern Anal Mach Intell 42(10):2624\u20132641","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"11224_CR28","doi-asserted-by":"crossref","unstructured":"Ranjan A, Jampani V, Balles L, Kim K, Sun D, Wulff J, Black MJ (2019) Competitive collaboration: Joint unsupervised learning of depth, camera motion, optical flow and motion segmentation. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 12240\u201312249","DOI":"10.1109\/CVPR.2019.01252"},{"issue":"10","key":"11224_CR29","doi-asserted-by":"publisher","first-page":"2586","DOI":"10.1007\/s12555-018-0926-8","volume":"17","author":"J-N Zhang","year":"2019","unstructured":"Zhang J-N, Su Q-X, Liu P-Y, Ge H-Y, Zhang Z-F (2019) Mudeepnet: unsupervised learning of dense depth, optical flow and camera pose using multi-view consistency loss. Int J Control Autom Syst 17(10):2586\u20132596","journal-title":"Int J Control Autom Syst"},{"key":"11224_CR30","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: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 340\u2013349","DOI":"10.1109\/CVPR.2018.00043"},{"key":"11224_CR31","doi-asserted-by":"crossref","unstructured":"Li R, Wang S, Long Z, Gu D (2018) Undeepvo: Monocular visual odometry through unsupervised deep learning. In: 2018 IEEE international conference on robotics and automation (ICRA), pp 7286\u20137291. IEEE","DOI":"10.1109\/ICRA.2018.8461251"},{"key":"11224_CR32","doi-asserted-by":"crossref","unstructured":"Zhou T, Brown M, Snavely N, Lowe DG (2017) Unsupervised learning of depth and ego-motion from video. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 1851\u20131858","DOI":"10.1109\/CVPR.2017.700"},{"issue":"4","key":"11224_CR33","doi-asserted-by":"publisher","first-page":"541","DOI":"10.1162\/neco.1989.1.4.541","volume":"1","author":"Y LeCun","year":"1989","unstructured":"LeCun Y, Boser B, Denker JS, Henderson D, Howard RE, Hubbard W, Jackel LD (1989) Backpropagation applied to handwritten zip code recognition. Neural Comput 1(4):541\u2013551","journal-title":"Neural Comput"},{"key":"11224_CR34","doi-asserted-by":"crossref","unstructured":"Kendall A, Grimes M, Cipolla R (2015) Posenet: A convolutional network for real-time 6-dof camera relocalization. In: Proceedings of the IEEE international conference on computer vision, pp 2938\u20132946","DOI":"10.1109\/ICCV.2015.336"},{"key":"11224_CR35","doi-asserted-by":"crossref","unstructured":"Kendall A, Cipolla R (2017) Geometric loss functions for camera pose regression with deep learning. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 5974\u20135983","DOI":"10.1109\/CVPR.2017.694"},{"issue":"2","key":"11224_CR36","doi-asserted-by":"publisher","first-page":"263","DOI":"10.1162\/neco.1989.1.2.263","volume":"1","author":"BA Pearlmutter","year":"1989","unstructured":"Pearlmutter BA (1989) Learning state space trajectories in recurrent neural networks. Neural Comput 1(2):263\u2013269","journal-title":"Neural Comput"},{"issue":"8","key":"11224_CR37","doi-asserted-by":"publisher","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","volume":"9","author":"S Hochreiter","year":"1997","unstructured":"Hochreiter S, Schmidhuber J (1997) Long short-term memory. Neural Comput 9(8):1735\u20131780","journal-title":"Neural Comput"},{"key":"11224_CR38","doi-asserted-by":"crossref","unstructured":"Walch F, Hazirbas C, Leal-Taixe L, Sattler T, Hilsenbeck S, Cremers D (2017) Image-based localization using lstms for structured feature correlation. In: Proceedings of the IEEE international conference on computer vision, pp 627\u2013637","DOI":"10.1109\/ICCV.2017.75"},{"key":"11224_CR39","doi-asserted-by":"crossref","unstructured":"Clark R, Wang S, Markham A, Trigoni N, Wen H (2017) Vidloc: A deep spatio-temporal model for 6-dof video-clip relocalization. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 6856\u20136864","DOI":"10.1109\/CVPR.2017.284"},{"key":"11224_CR40","doi-asserted-by":"crossref","unstructured":"Dosovitskiy A, Fischer P, Ilg E, Hausser P, Hazirbas C, Golkov V, Van\u00a0Der\u00a0Smagt P, Cremers D, Brox T (2015) Flownet: Learning optical flow with convolutional networks. In: Proceedings of the IEEE international conference on computer vision, pp 2758\u20132766","DOI":"10.1109\/ICCV.2015.316"},{"key":"11224_CR41","unstructured":"Eigen D, Puhrsch C, Fergus R (2014) Depth map prediction from a single image using a multi-scale deep network. Adv Neural Inf Process Syst. 27"},{"key":"11224_CR42","doi-asserted-by":"crossref","unstructured":"Agrawal P, Carreira J, Malik J (2015) Learning to see by moving. In: Proceedings of the IEEE international conference on computer vision, pp 37\u201345","DOI":"10.1109\/ICCV.2015.13"},{"key":"11224_CR43","doi-asserted-by":"crossref","unstructured":"Liu F, Shen C, Lin G (2015) Deep convolutional neural fields for depth estimation from a single image. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 5162\u20135170","DOI":"10.1109\/CVPR.2015.7299152"},{"issue":"10","key":"11224_CR44","doi-asserted-by":"publisher","first-page":"2024","DOI":"10.1109\/TPAMI.2015.2505283","volume":"38","author":"F Liu","year":"2015","unstructured":"Liu F, Shen C, Lin G, Reid I (2015) Learning depth from single monocular images using deep convolutional neural fields. IEEE Trans Pattern Anal Mach Intell 38(10):2024\u20132039","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"11224_CR45","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: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 5038\u20135047","DOI":"10.1109\/CVPR.2017.596"},{"key":"11224_CR46","doi-asserted-by":"crossref","unstructured":"Yin Z, Shi J (2018) Geonet: Unsupervised learning of dense depth, optical flow and camera pose. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 1983\u20131992","DOI":"10.1109\/CVPR.2018.00212"},{"key":"11224_CR47","doi-asserted-by":"crossref","unstructured":"Godard C, Mac\u00a0Aodha O, Brostow GJ (2017) Unsupervised monocular depth estimation with left-right consistency. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 270\u2013279","DOI":"10.1109\/CVPR.2017.699"},{"key":"11224_CR48","doi-asserted-by":"crossref","unstructured":"Zou Y, Luo Z, Huang J-B (2018) Df-net: Unsupervised joint learning of depth and flow using cross-task consistency. In: Proceedings of the European conference on computer vision (ECCV), pp 36\u201353","DOI":"10.1007\/978-3-030-01228-1_3"},{"key":"11224_CR49","doi-asserted-by":"crossref","unstructured":"Chen Y, Schmid C, Sminchisescu C (2019) Self-supervised learning with geometric constraints in monocular video: Connecting flow, depth, and camera. In: Proceedings of the IEEE\/CVF international conference on computer vision, pp 7063\u20137072","DOI":"10.1109\/ICCV.2019.00716"},{"key":"11224_CR50","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: 2019 international conference on robotics and automation (ICRA), pp 5474\u20135480. IEEE","DOI":"10.1109\/ICRA.2019.8793512"},{"issue":"11","key":"11224_CR51","doi-asserted-by":"publisher","first-page":"139","DOI":"10.1145\/3422622","volume":"63","author":"I Goodfellow","year":"2020","unstructured":"Goodfellow I, Pouget-Abadie J, Mirza M, Xu B, Warde-Farley D, Ozair S, Courville A, Bengio Y (2020) Generative adversarial networks. Commun ACM 63(11):139\u2013144","journal-title":"Commun ACM"},{"key":"11224_CR52","doi-asserted-by":"crossref","unstructured":"Li S, Xue F, Wang X, Yan Z, Zha H (2019) Sequential adversarial learning for self-supervised deep visual odometry. In: Proceedings of the IEEE\/CVF international conference on computer vision, pp 2851\u20132860","DOI":"10.1109\/ICCV.2019.00294"},{"key":"11224_CR53","doi-asserted-by":"crossref","unstructured":"Sun D, Yang X, Liu M-Y, Kautz J (2018) Pwc-net: Cnns for optical flow using pyramid, warping, and cost volume. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 8934\u20138943","DOI":"10.1109\/CVPR.2018.00931"},{"key":"11224_CR54","doi-asserted-by":"crossref","unstructured":"Godard C, Mac\u00a0Aodha O, Firman M, Brostow GJ (2019) Digging into self-supervised monocular depth estimation. In: Proceedings of the IEEE\/CVF international conference on computer vision, pp 3828\u20133838","DOI":"10.1109\/ICCV.2019.00393"},{"key":"11224_CR55","unstructured":"Ranftl R, Lasinger K, Hafner D, Schindler K, Koltun V (2020) Towards robust monocular depth estimation: Mixing datasets for zero-shot cross-dataset transfer. IEEE Trans Pattern Anal Mach Intell"},{"issue":"12","key":"11224_CR56","doi-asserted-by":"publisher","first-page":"4229","DOI":"10.1109\/TPAMI.2020.2974454","volume":"43","author":"Z Li","year":"2020","unstructured":"Li Z, Dekel T, Cole F, Tucker R, Snavely N, Liu C, Freeman WT (2020) Mannequinchallenge: learning the depths of moving people by watching frozen people. IEEE Trans Pattern Anal Mach Intell 43(12):4229\u20134241","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"11224_CR57","doi-asserted-by":"crossref","unstructured":"Klodt M, Vedaldi A (2018) Supervising the new with the old: learning sfm from sfm. In: Proceedings of the European conference on computer vision (ECCV), pp 698\u2013713","DOI":"10.1007\/978-3-030-01249-6_43"},{"key":"11224_CR58","doi-asserted-by":"crossref","unstructured":"Li Z, Snavely N (2018) Megadepth: Learning single-view depth prediction from internet photos. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 2041\u20132050","DOI":"10.1109\/CVPR.2018.00218"},{"key":"11224_CR59","unstructured":"Lucas BD, Kanade T, et\u00a0al (1981) An iterative image registration technique with an application to stereo vision vol. 81. Vancouver"},{"key":"11224_CR60","unstructured":"Jaderberg M, Simonyan K, Zisserman A, et al. (2015) Spatial transformer networks. Adv Neural Inf Process Syst 28"},{"key":"11224_CR61","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: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 5667\u20135675","DOI":"10.1109\/CVPR.2018.00594"},{"key":"11224_CR62","doi-asserted-by":"crossref","unstructured":"Garg R, Bg VK, Carneiro G, Reid I (2016) Unsupervised cnn for single view depth estimation: geometry to the rescue. In: European conference on computer vision, pp 740\u2013756. Springer","DOI":"10.1007\/978-3-319-46484-8_45"},{"issue":"6","key":"11224_CR63","doi-asserted-by":"publisher","first-page":"580","DOI":"10.1109\/34.601246","volume":"19","author":"RI Hartley","year":"1997","unstructured":"Hartley RI (1997) In defense of the eight-point algorithm. IEEE Trans Pattern Anal Mach Intell 19(6):580\u2013593","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"11224_CR64","doi-asserted-by":"crossref","unstructured":"Garg R, Wadhwa N, Ansari S, Barron JT (2019) Learning single camera depth estimation using dual-pixels. In: Proceedings of the IEEE\/CVF international conference on computer vision, pp 7628\u20137637","DOI":"10.1109\/ICCV.2019.00772"},{"issue":"1\u20132","key":"11224_CR65","doi-asserted-by":"publisher","first-page":"225","DOI":"10.1080\/757582976","volume":"21","author":"T Lindeberg","year":"1994","unstructured":"Lindeberg T (1994) Scale-space theory: a basic tool for analyzing structures at different scales. J Appl Stat 21(1\u20132):225\u2013270","journal-title":"J Appl Stat"},{"issue":"11","key":"11224_CR66","doi-asserted-by":"publisher","first-page":"1231","DOI":"10.1177\/0278364913491297","volume":"32","author":"A Geiger","year":"2013","unstructured":"Geiger A, Lenz P, Stiller C, Urtasun R (2013) Vision meets robotics: the kitti dataset. Int J Rob. Res. 32(11):1231\u20131237","journal-title":"Int J Rob. Res."},{"key":"11224_CR67","unstructured":"Paszke A, Gross S, Chintala S, Chanan G, Yang E, DeVito Z, Lin Z, Desmaison A, Antiga L, Lerer A (2017) Automatic differentiation in pytorch"},{"key":"11224_CR68","unstructured":"Kingma DP, Ba J (2014) Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980"},{"key":"11224_CR69","doi-asserted-by":"crossref","unstructured":"Ranjan A, Black MJ (2017) Optical flow estimation using a spatial pyramid network. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 4161\u20134170","DOI":"10.1109\/CVPR.2017.291"},{"key":"11224_CR70","doi-asserted-by":"crossref","unstructured":"Ilg E, Mayer N, Saikia T, Keuper M, Dosovitskiy A, Brox T (2017) Flownet 2.0: Evolution of optical flow estimation with deep networks. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp.2462\u20132470","DOI":"10.1109\/CVPR.2017.179"},{"key":"11224_CR71","doi-asserted-by":"crossref","unstructured":"Janai J, Guney F, Ranjan A, Black M, Geiger A (2018) Unsupervised learning of multi-frame optical flow with occlusions. In: Proceedings of the European conference on computer vision (ECCV), pp 690\u2013706","DOI":"10.1007\/978-3-030-01270-0_42"},{"key":"11224_CR72","doi-asserted-by":"crossref","unstructured":"Meister S, Hur J, Roth S (2018) Unflow: Unsupervised learning of optical flow with a bidirectional census loss. In: Proceedings of the AAAI conference on artificial intelligence, vol 32","DOI":"10.1609\/aaai.v32i1.12276"},{"key":"11224_CR73","doi-asserted-by":"crossref","unstructured":"Geiger A, Ziegler J, Stiller C (2011) Stereoscan: Dense 3d reconstruction in real-time. In: 2011 IEEE intelligent vehicles symposium (IV), pp 963\u2013968. Ieee","DOI":"10.1109\/IVS.2011.5940405"},{"key":"11224_CR74","doi-asserted-by":"publisher","first-page":"376","DOI":"10.1109\/34.88573","volume":"13","author":"S Umeyama","year":"1991","unstructured":"Umeyama S (1991) Least-squares estimation of transformation parameters between two point patterns. IEEE Trans Pattern Anal Mach Intell 13:376\u2013380","journal-title":"IEEE Trans Pattern Anal Mach Intell"}],"container-title":["Neural Processing Letters"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11063-023-11224-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11063-023-11224-1\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11063-023-11224-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,11]],"date-time":"2023-11-11T17:12:29Z","timestamp":1699722749000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11063-023-11224-1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,3,13]]},"references-count":74,"journal-issue":{"issue":"7","published-print":{"date-parts":[[2023,12]]}},"alternative-id":["11224"],"URL":"https:\/\/doi.org\/10.1007\/s11063-023-11224-1","relation":{},"ISSN":["1370-4621","1573-773X"],"issn-type":[{"value":"1370-4621","type":"print"},{"value":"1573-773X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,3,13]]},"assertion":[{"value":"27 February 2023","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"13 March 2023","order":2,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}