{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,4]],"date-time":"2025-11-04T11:03:19Z","timestamp":1762254199885,"version":"3.37.3"},"reference-count":49,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2022,7,28]],"date-time":"2022-07-28T00:00:00Z","timestamp":1658966400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,7,28]],"date-time":"2022-07-28T00:00:00Z","timestamp":1658966400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key R&D Program of China","doi-asserted-by":"crossref","award":["2020YFB1313002"],"award-info":[{"award-number":["2020YFB1313002"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61973029"],"award-info":[{"award-number":["61973029"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Scientific and Technological Innovation Foundation of Foshan","award":["BK21BF004"],"award-info":[{"award-number":["BK21BF004"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J Intell Robot Syst"],"published-print":{"date-parts":[[2022,8]]},"DOI":"10.1007\/s10846-022-01685-2","type":"journal-article","created":{"date-parts":[[2022,7,28]],"date-time":"2022-07-28T12:56:34Z","timestamp":1659012994000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":6,"title":["Keypoint Heatmap Guided Self-Supervised Monocular Visual Odometry"],"prefix":"10.1007","volume":"105","author":[{"given":"Haixin","family":"Xiu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yiyou","family":"Liang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4137-7424","authenticated-orcid":false,"given":"Hui","family":"Zeng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2022,7,28]]},"reference":[{"key":"1685_CR1","doi-asserted-by":"publisher","first-page":"1147","DOI":"10.1109\/TRO.2015.2463671","volume":"31","author":"R Mur-Artal","year":"2015","unstructured":"Mur-Artal, R., Montiel, J.M.M., Tardos, J.D.: ORB-SLAM: a versatile and accurate monocular SLAM system. IEEE Trans. Robot. 31, 1147\u20131163 (2015). https:\/\/doi.org\/10.1109\/TRO.2015.2463671","journal-title":"IEEE Trans. Robot."},{"key":"1685_CR2","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., Tardos, J.D.: ORB-SLAM2: an open-source SLAM system for monocular, stereo, and RGB-D cameras. IEEE Trans. Robot. 33, 1255\u20131262 (2017). https:\/\/doi.org\/10.1109\/TRO.2017.2705103","journal-title":"IEEE Trans. Robot."},{"key":"1685_CR3","doi-asserted-by":"publisher","first-page":"1874","DOI":"10.1109\/TRO.2021.3075644","volume":"37","author":"C Campos","year":"2021","unstructured":"Campos, C., Elvira, R., Rodr\u00edguez, J.J.G., Montiel, J.M.M., Tard\u00f3s, J.D.: ORB-SLAM3: an accurate open-source library for visual, visual-inertial, and multimap SLAM. IEEE Trans. Robot. 37, 1874\u20131890 (2021). https:\/\/doi.org\/10.1109\/TRO.2021.3075644","journal-title":"IEEE Trans. Robot."},{"key":"1685_CR4","doi-asserted-by":"publisher","first-page":"2980","DOI":"10.1109\/ICCV.2017.322","volume-title":"Proceedings - IEEE\/CVF International Conference on Computer Vision (ICCV)","author":"K He","year":"2017","unstructured":"He, K., Gkioxari, G., Doll\u00e1r, P., Girshick, R.: Mask R-CNN. In: Proceedings - IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 2980\u20132988. IEEE (2017). https:\/\/doi.org\/10.1109\/ICCV.2017.322"},{"key":"1685_CR5","doi-asserted-by":"publisher","unstructured":"Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. IEEE Trans. Pattern Anal. Mach. Intell. 39(1137\u20131149), (2017). https:\/\/doi.org\/10.1109\/TPAMI.2016.2577031","DOI":"10.1109\/TPAMI.2016.2577031"},{"key":"1685_CR6","doi-asserted-by":"publisher","first-page":"337","DOI":"10.1109\/CVPRW.2018.00060","volume-title":"Proceedings - IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)","author":"D DeTone","year":"2018","unstructured":"DeTone, D., Malisiewicz, T., Rabinovich, A.: SuperPoint: self-supervised interest point detection and description. In: Proceedings - IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), pp. 337\u2013345. IEEE (2018). https:\/\/doi.org\/10.1109\/CVPRW.2018.00060"},{"key":"1685_CR7","doi-asserted-by":"publisher","first-page":"4937","DOI":"10.1109\/CVPR42600.2020.00499","volume-title":"Proceedings - IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","author":"P-E Sarlin","year":"2020","unstructured":"Sarlin, P.-E., DeTone, D., Malisiewicz, T., Rabinovich, A.: SuperGlue: learning feature matching with graph neural networks. In: Proceedings - IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 4937\u20134946. IEEE (2020). https:\/\/doi.org\/10.1109\/CVPR42600.2020.00499"},{"key":"1685_CR8","first-page":"6992","volume-title":"Advances in Neural Information Processing Systems","author":"Y Liu","year":"2019","unstructured":"Liu, Y., Shen, Z., Lin, Z., Peng, S., Bao, H., Zhou, X.: GIFT: learning transformation-invariant dense visual descriptors via group CNNs. In: Advances in Neural Information Processing Systems, pp. 6992\u20137003. MIT Press (2019) https:\/\/dl.acm.org\/doi\/10.5555\/3454287.3454915"},{"key":"1685_CR9","doi-asserted-by":"publisher","first-page":"8084","DOI":"10.1109\/CVPR.2019.00828","volume-title":"Proceedings - IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","author":"M Dusmanu","year":"2019","unstructured":"Dusmanu, M., Rocco, I., Pajdla, T., Pollefeys, M., Sivic, J., Torii, A., Sattler, T.: D2-net: a trainable CNN for joint description and detection of local features. In: Proceedings - IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 8084\u20138093. IEEE (2019). https:\/\/doi.org\/10.1109\/CVPR.2019.00828"},{"key":"1685_CR10","doi-asserted-by":"publisher","first-page":"6612","DOI":"10.1109\/CVPR.2017.700","volume-title":"Proceedings - IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","author":"T Zhou","year":"2017","unstructured":"Zhou, T., Brown, M., Snavely, N., Lowe, D.G.: Unsupervised learning of depth and Ego-motion from video. In: Proceedings - IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 6612\u20136619. IEEE (2017). https:\/\/doi.org\/10.1109\/CVPR.2017.700"},{"key":"1685_CR11","first-page":"1","volume-title":"Advances in Neural Information Processing Systems","author":"J-W Bian","year":"2019","unstructured":"Bian, J.-W., Li, Z., Wang, N., Zhan, H., Shen, C., Cheng, M.-M., Reid, I.: Unsupervised scale-consistent depth and ego-motion learning from monocular video. In: Wallach, H., Larochelle, H., Beygelzimer, A., d\u2019Alche-Buc, F., Fox, E., Garnett, R. (eds.) Advances in Neural Information Processing Systems, pp. 1\u201311. MIT Press, Vancouver (2019)"},{"key":"1685_CR12","doi-asserted-by":"publisher","first-page":"5474","DOI":"10.1109\/ICRA.2019.8793512","volume-title":"Proceedings - IEEE International Conference on Robotics and Automation (ICRA)","author":"Y Almalioglu","year":"2019","unstructured":"Almalioglu, Y., Saputra, M.R.U., De Gusm\u00e3o, P.P.B., Markham, A., Trigoni, N.: GANVO: unsupervised deep monocular visual odometry and depth estimation with generative adversarial networks. In: Proceedings - IEEE International Conference on Robotics and Automation (ICRA), pp. 5474\u20135480. IEEE (2019). https:\/\/doi.org\/10.1109\/ICRA.2019.8793512"},{"key":"1685_CR13","doi-asserted-by":"publisher","first-page":"1983","DOI":"10.1109\/CVPR.2018.00212","volume-title":"Proceedings - IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","author":"Z Yin","year":"2018","unstructured":"Yin, Z., Shi, J.: GeoNet: unsupervised learning of dense depth, optical flow and camera pose. In: Proceedings - IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1983\u20131992. IEEE (2018). https:\/\/doi.org\/10.1109\/CVPR.2018.00212"},{"key":"1685_CR14","doi-asserted-by":"publisher","first-page":"2320","DOI":"10.1109\/ICCV.2011.6126513","volume-title":"Proceedings - IEEE\/CVF International Conference on Computer Vision (ICCV)","author":"RA Newcombe","year":"2011","unstructured":"Newcombe, R.A., Lovegrove, S.J., Davison, A.J.: DTAM: dense tracking and mapping in real-time. In: Proceedings - IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 2320\u20132327. IEEE (2011). https:\/\/doi.org\/10.1109\/ICCV.2011.6126513"},{"key":"1685_CR15","doi-asserted-by":"publisher","first-page":"1150","DOI":"10.1109\/ICCV.1999.790410","volume-title":"Proceedings - IEEE\/CVF International Conference on Computer Vision (ICCV)","author":"DG Lowe","year":"1999","unstructured":"Lowe, D.G.: Object recognition from local scale-invariant features. In: Proceedings - IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 1150\u20131157. IEEE (1999). https:\/\/doi.org\/10.1109\/ICCV.1999.790410"},{"key":"1685_CR16","doi-asserted-by":"publisher","first-page":"127","DOI":"10.1109\/ISMAR.2011.6092378","volume-title":"Proceedings - 2011 10th IEEE International Symposium on Mixed and Augmented Reality","author":"RA Newcombe","year":"2011","unstructured":"Newcombe, R.A., Fitzgibbon, A., Izadi, S., Hilliges, O., Molyneaux, D., Kim, D., Davison, A.J., Kohi, P., Shotton, J., Hodges, S.: KinectFusion: real-time dense surface mapping and tracking. In: Proceedings - 2011 10th IEEE International Symposium on Mixed and Augmented Reality, pp. 127\u2013136. IEEE (2011). https:\/\/doi.org\/10.1109\/ISMAR.2011.6092378"},{"key":"1685_CR17","doi-asserted-by":"publisher","first-page":"3923","DOI":"10.1109\/ICCV.2017.421","volume-title":"Proceedings - IEEE\/CVF International Conference on Computer Vision (ICCV)","author":"R Wang","year":"2017","unstructured":"Wang, R., Schworer, M., Cremers, D.: Stereo DSO: large-scale direct sparse visual odometry with stereo cameras. In: Proceedings - IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 3923\u20133931. IEEE (2017). https:\/\/doi.org\/10.1109\/ICCV.2017.421"},{"key":"1685_CR18","doi-asserted-by":"publisher","first-page":"2510","DOI":"10.1109\/ICRA.2018.8462905","volume-title":"Proceedings - IEEE International Conference on Robotics and Automation (ICRA)","author":"L Von Stumberg","year":"2018","unstructured":"Von Stumberg, L., Usenko, V., Cremers, D.: Direct sparse visual-inertial odometry using dynamic marginalization. In: Proceedings - IEEE International Conference on Robotics and Automation (ICRA), pp. 2510\u20132517. IEEE (2018). https:\/\/doi.org\/10.1109\/ICRA.2018.8462905"},{"key":"1685_CR19","doi-asserted-by":"publisher","first-page":"611","DOI":"10.1109\/TPAMI.2017.2658577","volume":"40","author":"J Engel","year":"2018","unstructured":"Engel, J., Koltun, V., Cremers, D.: Direct sparse odometry. IEEE Trans. Pattern Anal. Mach. Intell. 40, 611\u2013625 (2018). https:\/\/doi.org\/10.1109\/TPAMI.2017.2658577","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"1685_CR20","doi-asserted-by":"publisher","first-page":"834","DOI":"10.1007\/978-3-319-10605-2_54","volume-title":"European Conference on Computer Vision (ECCV)","author":"J Engel","year":"2014","unstructured":"Engel, J., Sch\u00f6ps, T., Cremers, D.: LSD-SLAM: Large-scale direct monocular SLAM. In: European Conference on Computer Vision (ECCV), pp. 834\u2013849. Springer (2014). https:\/\/doi.org\/10.1007\/978-3-319-10605-2_54"},{"key":"1685_CR21","doi-asserted-by":"publisher","first-page":"1052","DOI":"10.1109\/TPAMI.2007.1049","volume":"29","author":"AJ Davison","year":"2007","unstructured":"Davison, A.J., Reid, I.D., Molton, N.D., Stasse, O.: MonoSLAM: real-time single camera SLAM. IEEE Trans. Pattern Anal. Machine Intell. 29, 1052\u20131067 (2007)","journal-title":"IEEE Trans. Pattern Anal. Machine Intell."},{"key":"1685_CR22","doi-asserted-by":"publisher","first-page":"3710","DOI":"10.1109\/ROBOT.2008.4543780","volume-title":"Proceedings - IEEE International Conference on Robotics and Automation","author":"S Holmes","year":"2008","unstructured":"Holmes, S., Klein, G., Murray, D.W.: A square root unscented kalman filter for visual monoSLAM. In: Proceedings - IEEE International Conference on Robotics and Automation, pp. 3710\u20133716. IEEE (2008). https:\/\/doi.org\/10.1109\/ROBOT.2008.4543780"},{"key":"1685_CR23","doi-asserted-by":"publisher","first-page":"1365","DOI":"10.1109\/IROS.2015.7353545","volume-title":"Proceedings - IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","author":"D Gamage","year":"2015","unstructured":"Gamage, D., Drummond, T.: Reduced dimensionality extended Kalman filter for SLAM in a relative formulation. In: Proceedings - IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 1365\u20131372. IEEE (2015). https:\/\/doi.org\/10.1109\/IROS.2015.7353545"},{"key":"1685_CR24","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/ISMAR.2007.4538852","volume-title":"Proceedings - IEEE and ACM International Symposium on Mixed and Augmented Reality","author":"G Klein","year":"2007","unstructured":"Klein, G., Murray, D.: Parallel tracking and mapping for small AR workspaces. In: Proceedings - IEEE and ACM International Symposium on Mixed and Augmented Reality, pp. 1\u201310. IEEE (2007). https:\/\/doi.org\/10.1109\/ISMAR.2007.4538852"},{"key":"1685_CR25","doi-asserted-by":"publisher","first-page":"1449","DOI":"10.1109\/ICCV.2013.183","volume-title":"Proceedings - IEEE\/CVF International Conference on Computer Vision (ICCV)","author":"J Engel","year":"2013","unstructured":"Engel, J., Sturm, J., Cremers, D.: Semi-dense visual odometry for a monocular camera. In: Proceedings - IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 1449\u20131456. IEEE (2013). https:\/\/doi.org\/10.1109\/ICCV.2013.183"},{"key":"1685_CR26","doi-asserted-by":"publisher","first-page":"2043","DOI":"10.1109\/ICRA.2017.7989236","volume-title":"Proceedings - IEEE International Conference on Robotics and Automation (ICRA)","author":"S Wang","year":"2017","unstructured":"Wang, S., Clark, R., Wen, H., Trigoni, N.: Deepvo: towards end-to-end visual odometry with deep recurrent convolutional neural networks. In: Proceedings - IEEE International Conference on Robotics and Automation (ICRA), pp. 2043\u20132050. IEEE (2017). https:\/\/doi.org\/10.1109\/ICRA.2017.7989236"},{"key":"1685_CR27","doi-asserted-by":"publisher","first-page":"8567","DOI":"10.1109\/CVPR.2019.00877","volume-title":"Proceedings - IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","author":"F Xue","year":"2019","unstructured":"Xue, F., Wang, X., Li, S., Wang, Q., Wang, J., Zha, H.: Beyond tracking: selecting memory and refining poses for deep visual odometry. In: Proceedings - IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 8567\u20138575. IEEE (2019). https:\/\/doi.org\/10.1109\/CVPR.2019.00877"},{"key":"1685_CR28","doi-asserted-by":"publisher","first-page":"5622","DOI":"10.1109\/CVPR.2017.596","volume-title":"Proceedings - IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","author":"B Ummenhofer","year":"2017","unstructured":"Ummenhofer, B., Zhou, H., Uhrig, J., Mayer, N., Ilg, E., Dosovitskiy, A., Brox, T.: DeMoN: depth and motion network for learning monocular stereo. In: Proceedings - IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 5622\u20135631. IEEE (2017). https:\/\/doi.org\/10.1109\/CVPR.2017.596"},{"key":"1685_CR29","doi-asserted-by":"publisher","first-page":"710","DOI":"10.1007\/978-3-030-58568-6_42","volume-title":"Computer Vision \u2013 ECCV 2020","author":"Y Zou","year":"2020","unstructured":"Zou, Y., Ji, P., Tran, Q.-H., Huang, J.-B., Chandraker, M.: Learning monocular visual odometry via self-supervised long-term modeling. In: Computer Vision \u2013 ECCV 2020, pp. 710\u2013727. Springer (2020). https:\/\/doi.org\/10.1007\/978-3-030-58568-6_42"},{"key":"1685_CR30","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/978-3-030-01270-0_50","volume-title":"European Conference on Computer Vision (ECCV)","author":"H Zhou","year":"2018","unstructured":"Zhou, H., Ummenhofer, B., Brox, T.: DeepTAM: deep tracking and mapping. In: European Conference on Computer Vision (ECCV), pp. 1\u201318. Springer (2018). https:\/\/doi.org\/10.1007\/978-3-030-01270-0_50"},{"key":"1685_CR31","doi-asserted-by":"publisher","first-page":"7286","DOI":"10.1109\/ICRA.2018.8461251","volume-title":"Proceedings - IEEE International Conference on Robotics and Automation (ICRA)","author":"R Li","year":"2018","unstructured":"Li, R., Wang, S., Long, Z., Gu, D.: UnDeepVO: monocular visual odometry through unsupervised deep learning. In: Proceedings - IEEE International Conference on Robotics and Automation (ICRA), pp. 7286\u20137291. IEEE (2018). https:\/\/doi.org\/10.1109\/ICRA.2018.8461251"},{"key":"1685_CR32","doi-asserted-by":"publisher","first-page":"5555","DOI":"10.1109\/CVPR.2019.00570","volume-title":"Proceedings - IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","author":"R Wang","year":"2019","unstructured":"Wang, R., Pizer, S.M., Frahm, J.-M.: Recurrent neural network for (un-)supervised learning of monocular video visual odometry and depth. In: Proceedings - IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 5555\u20135564. IEEE (2019). https:\/\/doi.org\/10.1109\/CVPR.2019.00570"},{"key":"1685_CR33","first-page":"802","volume-title":"Advances in Neural Information Processing Systems","author":"X Shi","year":"2015","unstructured":"Shi, X., Chen, Z., Wang, H., Yeung, D.-Y., Wong, W., Woo, W.: Convolutional LSTM network: a machine learning approach for precipitation nowcasting. In: Advances in Neural Information Processing Systems, pp. 802\u2013810. MIT Press (2015)"},{"key":"1685_CR34","doi-asserted-by":"publisher","first-page":"4950","DOI":"10.1109\/IROS45743.2020.9341229","volume-title":"Proceedings - IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","author":"Y-Y Jau","year":"2020","unstructured":"Jau, Y.-Y., Zhu, R., Su, H., Chandraker, M.: Deep keypoint-based camera pose estimation with geometric constraints. In: Proceedings - IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 4950\u20134957. IEEE (2020). https:\/\/doi.org\/10.1109\/IROS45743.2020.9341229"},{"key":"1685_CR35","doi-asserted-by":"publisher","first-page":"77","DOI":"10.1109\/CVPR.2017.16","volume-title":"Proceedings - IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","author":"RQ Charles","year":"2017","unstructured":"Charles, R.Q., Su, H., Kaichun, M., Guibas, L.J.: PointNet: deep learning on point sets for 3d classification and segmentation. In: Proceedings - IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 77\u201385. IEEE (2017). https:\/\/doi.org\/10.1109\/CVPR.2017.16"},{"key":"1685_CR36","doi-asserted-by":"publisher","unstructured":"Wang, Z., Bovik, A.C., Sheikh, H.R., Simoncelli, E.P.: Image quality assessment: from error visibility to structural similarity. IEEE Trans. Image Process. 13(600\u2013612), (2004). https:\/\/doi.org\/10.1109\/TIP.2003.819861","DOI":"10.1109\/TIP.2003.819861"},{"key":"1685_CR37","doi-asserted-by":"publisher","first-page":"6602","DOI":"10.1109\/CVPR.2017.699","volume-title":"Proceedings - IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","author":"C Godard","year":"2017","unstructured":"Godard, C., Aodha, O.M., Brostow, G.J.: Unsupervised monocular depth estimation with left-right consistency. In: Proceedings - IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 6602\u20136611. IEEE (2017). https:\/\/doi.org\/10.1109\/CVPR.2017.699"},{"key":"1685_CR38","doi-asserted-by":"publisher","first-page":"770","DOI":"10.1109\/CVPR.2016.90","volume-title":"Proceedings - IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","author":"K He","year":"2016","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings - IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 770\u2013778. IEEE (2016). https:\/\/doi.org\/10.1109\/CVPR.2016.90"},{"key":"1685_CR39","doi-asserted-by":"publisher","first-page":"211","DOI":"10.1007\/s11263-015-0816-y","volume":"115","author":"O Russakovsky","year":"2015","unstructured":"Russakovsky, O., Deng, J., Su, H., Krause, J., Satheesh, S., Ma, S., Huang, Z., Karpathy, A., Khosla, A., Bernstein, M., Berg, A.C., Fei-Fei, L.: imagenet large scale visual recognition challenge. Int. J. Comput. Vis. 115, 211\u2013252 (2015). https:\/\/doi.org\/10.1007\/s11263-015-0816-y","journal-title":"Int. J. Comput. Vis."},{"key":"1685_CR40","doi-asserted-by":"publisher","first-page":"4040","DOI":"10.1109\/CVPR.2016.438","volume-title":"Proceedings - IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","author":"N Mayer","year":"2016","unstructured":"Mayer, N., Ilg, E., Hausser, P., Fischer, P., Cremers, D., Dosovitskiy, A., Brox, T.: A large dataset to train convolutional networks for disparity, optical flow, and scene flow estimation. In: Proceedings - IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 4040\u20134048. IEEE (2016). https:\/\/doi.org\/10.1109\/CVPR.2016.438"},{"key":"1685_CR41","doi-asserted-by":"publisher","first-page":"3354","DOI":"10.1109\/CVPR.2012.6248074","volume-title":"Proceedings - IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","author":"A Geiger","year":"2012","unstructured":"Geiger, A., Lenz, P., Urtasun, R.: Are we ready for autonomous driving? The KITTI vision benchmark suite. In: Proceedings - IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3354\u20133361. IEEE (2012). https:\/\/doi.org\/10.1109\/CVPR.2012.6248074"},{"key":"1685_CR42","doi-asserted-by":"publisher","first-page":"1","DOI":"10.48550\/ARXIV.1412.6980","volume-title":"International Conference on Learning Representations (ICLR)","author":"DP Kingma","year":"2015","unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. In: International Conference on Learning Representations (ICLR), pp. 1\u201315. ICLR, San Diego (2015). https:\/\/doi.org\/10.48550\/ARXIV.1412.6980"},{"key":"1685_CR43","doi-asserted-by":"publisher","first-page":"3827","DOI":"10.1109\/ICCV.2019.00393","volume-title":"Proceedings - IEEE\/CVF International Conference on Computer Vision (ICCV)","author":"C Godard","year":"2019","unstructured":"Godard, C., Mac Aodha, O., Firman, M., Brostow, G.: Digging into self-supervised monocular depth estimation. In: Proceedings - IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 3827\u20133837. IEEE (South) (2019). https:\/\/doi.org\/10.1109\/ICCV.2019.00393"},{"key":"1685_CR44","doi-asserted-by":"publisher","first-page":"340","DOI":"10.1109\/CVPR.2018.00043","volume-title":"Proceedings - IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","author":"H Zhan","year":"2018","unstructured":"Zhan, H., Garg, R., Weerasekera, C.S., Li, K., Agarwal, H., Reid, I.: Unsupervised learning of monocular depth estimation and visual odometry with deep feature reconstruction. In: Proceedings - IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 340\u2013349. IEEE (2018). https:\/\/doi.org\/10.1109\/CVPR.2018.00043"},{"key":"1685_CR45","doi-asserted-by":"publisher","first-page":"5667","DOI":"10.1109\/CVPR.2018.00594","volume-title":"Proceedings - IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","author":"R Mahjourian","year":"2018","unstructured":"Mahjourian, R., Wicke, M., Angelova, A.: Unsupervised learning of depth and ego-motion from monocular video using geometric constraints. In: Proceedings - IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 5667\u20135675. IEEE (2018). https:\/\/doi.org\/10.1109\/CVPR.2018.00594"},{"key":"1685_CR46","doi-asserted-by":"publisher","first-page":"12232","DOI":"10.1109\/CVPR.2019.01252","volume-title":"Proceedings - IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","author":"A Ranjan","year":"2019","unstructured":"Ranjan, A., Jampani, V., Balles, L., Kim, K., Sun, D., Wulff, J., Black, M.J.: Competitive collaboration: joint unsupervised learning of depth, camera motion, optical flow and motion segmentation. In: Proceedings - IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 12232\u201312241. IEEE (2019). https:\/\/doi.org\/10.1109\/CVPR.2019.01252"},{"key":"1685_CR47","doi-asserted-by":"publisher","first-page":"6359","DOI":"10.1109\/ICRA.2019.8793479","volume-title":"Proceedings - IEEE International Conference on Robotics and Automation (ICRA)","author":"T Shen","year":"2019","unstructured":"Shen, T., Luo, Z., Zhou, L., Deng, H., Zhang, R., Fang, T., Quan, L.: Beyond photometric loss for self-supervised ego-motion estimation. In: Proceedings - IEEE International Conference on Robotics and Automation (ICRA), pp. 6359\u20136365. IEEE (2019). https:\/\/doi.org\/10.1109\/ICRA.2019.8793479"},{"key":"1685_CR48","doi-asserted-by":"publisher","first-page":"5439","DOI":"10.1109\/ICRA.2019.8793706","volume-title":"Proceedings - IEEE International Conference on Robotics and Automation (ICRA)","author":"Y Li","year":"2019","unstructured":"Li, Y., Ushiku, Y., Harada, T.: Pose graph optimization for unsupervised monocular visual Odometry. In: Proceedings - IEEE International Conference on Robotics and Automation (ICRA), pp. 5439\u20135445. IEEE (2019). https:\/\/doi.org\/10.1109\/ICRA.2019.8793706"},{"key":"1685_CR49","doi-asserted-by":"publisher","first-page":"6338","DOI":"10.1109\/CVPR42600.2020.00637","volume-title":"Proceedings - IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","author":"S Li","year":"2020","unstructured":"Li, S., Wang, X., Cao, Y., Xue, F., Yan, Z., Zha, H.: Self-supervised deep visual Odometry with online adaptation. In: Proceedings - IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 6338\u20136347. IEEE (2020). https:\/\/doi.org\/10.1109\/CVPR42600.2020.00637"}],"container-title":["Journal of Intelligent & Robotic Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10846-022-01685-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10846-022-01685-2\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10846-022-01685-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,9,12]],"date-time":"2022-09-12T14:29:40Z","timestamp":1662992980000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10846-022-01685-2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,7,28]]},"references-count":49,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2022,8]]}},"alternative-id":["1685"],"URL":"https:\/\/doi.org\/10.1007\/s10846-022-01685-2","relation":{},"ISSN":["0921-0296","1573-0409"],"issn-type":[{"type":"print","value":"0921-0296"},{"type":"electronic","value":"1573-0409"}],"subject":[],"published":{"date-parts":[[2022,7,28]]},"assertion":[{"value":"4 February 2022","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"3 July 2022","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"28 July 2022","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"Not applicable.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethical Approval"}},{"value":"Not applicable.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent to Participate"}},{"value":"Not applicable.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent to Publish"}},{"value":"The authors declare that they have no conflicts of interest.","order":5,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflicts of Interest"}}],"article-number":"78"}}