{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T10:43:19Z","timestamp":1740134599734,"version":"3.37.3"},"reference-count":48,"publisher":"Informa UK Limited","issue":"2","funder":[{"DOI":"10.13039\/501100001691","name":"Japan Society for the Promotion of Science","doi-asserted-by":"publisher","award":["18F18109"],"award-info":[{"award-number":["18F18109"]}],"id":[{"id":"10.13039\/501100001691","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["www.tandfonline.com"],"crossmark-restriction":true},"short-container-title":["Advanced Robotics"],"published-print":{"date-parts":[[2021,1,17]]},"DOI":"10.1080\/01691864.2020.1857305","type":"journal-article","created":{"date-parts":[[2020,12,10]],"date-time":"2020-12-10T12:16:01Z","timestamp":1607602561000},"page":"118-128","update-policy":"https:\/\/doi.org\/10.1080\/tandf_crossmark_01","source":"Crossref","is-referenced-by-count":3,"title":["Self-supervised optical flow derotation network for rotation estimation of a spherical camera"],"prefix":"10.1080","volume":"35","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4854-0658","authenticated-orcid":false,"given":"Dabae","family":"Kim","sequence":"first","affiliation":[{"name":"Department of Precision Engineering, Graduate School of Engineering, The University of Tokyo, Tokyo, Japan"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5271-1782","authenticated-orcid":false,"given":"Sarthak","family":"Pathak","sequence":"additional","affiliation":[{"name":"Department of Precision Engineering, Graduate School of Engineering, The University of Tokyo, Tokyo, Japan"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8711-0330","authenticated-orcid":false,"given":"Alessandro","family":"Moro","sequence":"additional","affiliation":[{"name":"Department of Precision Engineering, Graduate School of Engineering, The University of Tokyo, Tokyo, Japan"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1280-069X","authenticated-orcid":false,"given":"Atsushi","family":"Yamashita","sequence":"additional","affiliation":[{"name":"Department of Precision Engineering, Graduate School of Engineering, The University of Tokyo, Tokyo, Japan"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9482-497X","authenticated-orcid":false,"given":"Hajime","family":"Asama","sequence":"additional","affiliation":[{"name":"Department of Precision Engineering, Graduate School of Engineering, The University of Tokyo, Tokyo, Japan"}]}],"member":"301","published-online":{"date-parts":[[2020,12,9]]},"reference":[{"key":"CIT0001","doi-asserted-by":"publisher","DOI":"10.1080\/01691864.2019.1610060"},{"key":"CIT0002","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2017.2705138"},{"key":"CIT0003","doi-asserted-by":"crossref","unstructured":"Clark R, Wang S, Wen H, et\u00a0al. VINet: visual-inertial odometry as a sequence-to-sequence learning problem. In: Proceedings of the 31th AAAI Conference on Artificial Intelligence (AAAI). 2017. p.\u00a03995\u20134001.","DOI":"10.1609\/aaai.v31i1.11215"},{"key":"CIT0004","doi-asserted-by":"crossref","unstructured":"Wang S, Clark R, Wen H, et\u00a0al. Towards end-to-end visual odomtery with deep recurrent convolutional neural networks. In: Proceedings of the 2017 IEEE International Conference on Robotics and Automation (ICRA). 2017. p.\u00a02043\u20132050.","DOI":"10.1109\/ICRA.2017.7989236"},{"key":"CIT0005","doi-asserted-by":"crossref","unstructured":"Kim D, Pathak S, Moro A, et\u00a0al. E-CNN: accurate spherical camera rotation estimation via uniformization of distorted optical flow fields. In: Proceedings of the 44th IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP). 2019. p.\u00a02232\u20132236.","DOI":"10.1109\/ICASSP.2019.8682203"},{"key":"CIT0006","unstructured":"Huang AS, Bachrach A, Henry P, et\u00a0al. Visual odometry and mapping for autonomous flight using an RGB-D camera. In: International Symposium on Robotics Research (ISRR). 2011."},{"key":"CIT0007","doi-asserted-by":"crossref","unstructured":"Schubert D, Goll T, Demmel N, et\u00a0al. The TUM VI benchmark for evaluating visual-inertial odometry. In: Proceedings of the 2018 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS). 2018. p.\u00a01680\u20131687.","DOI":"10.1109\/IROS.2018.8593419"},{"key":"CIT0008","doi-asserted-by":"publisher","DOI":"10.1177\/0278364913491297"},{"key":"CIT0009","doi-asserted-by":"crossref","unstructured":"Franke U, Pfeiffer D, Rabe C, et\u00a0al. Making bertha see. In: Proceedings of the 2013 IEEE International Conference on Computer Vision Workshops (ICCVW). 2013. p.\u00a0214\u2013221.","DOI":"10.1109\/ICCVW.2013.36"},{"key":"CIT0010","doi-asserted-by":"crossref","unstructured":"Caron G, Morbidi F. Spherical visual gyroscope for autonomous robots using the mixture of photometric potentials. In: Proceedings of the 2018 Ieee International Conference on Robotics and Automation (ICRA). 2018. p.\u00a0820\u2013827.","DOI":"10.1109\/ICRA.2018.8460761"},{"key":"CIT0011","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2893066"},{"key":"CIT0012","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2814344"},{"key":"CIT0013","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2018.2875943"},{"key":"CIT0014","doi-asserted-by":"crossref","unstructured":"Lee M, Fowlkes CC. CeMNet: Self-supervised learning for accurate continuous ego-motion estimation. In: Proceedings of the 2019 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW). 2019.","DOI":"10.1109\/CVPRW.2019.00048"},{"key":"CIT0015","doi-asserted-by":"crossref","unstructured":"Wang FE, Hu HN, Cheng HT, et\u00a0al. Self-supervised learning of depth and camera motion from 360\u2218 videos. In: Proceedings of the 14th Asian Conference on Computer Vision (ACCV). 2018. p.\u00a053\u201368.","DOI":"10.1007\/978-3-030-20873-8_4"},{"key":"CIT0016","doi-asserted-by":"crossref","unstructured":"Yin Z, Shi J. GeoNet: unsupervised learning of dense depth, optical flow and camera pose. In: Proceedings of the 2018 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Vol. 2. 2018. p.\u00a01983\u20131992.","DOI":"10.1109\/CVPR.2018.00212"},{"key":"CIT0017","doi-asserted-by":"crossref","unstructured":"Iyer G, Murthy JK, Gupta G, et\u00a0al. Geometric consistency for self-supervised end-to-end visual odometry. In: Proceedings of the 2018 IEEE Conference on Computer Vision and Pattern recognition Workshops (CVPRW). 2018. p.\u00a0380\u2013388.","DOI":"10.1109\/CVPRW.2018.00064"},{"key":"CIT0018","doi-asserted-by":"crossref","unstructured":"Yu C, Liu Z, Liu XJ, et\u00a0al. DS-SLAM: a semantic visual SLAM towards dynamic environments. In: Proceedings of the IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS). 2018. p.\u00a01168\u20131174.","DOI":"10.1109\/IROS.2018.8593691"},{"key":"CIT0019","doi-asserted-by":"crossref","unstructured":"Solin A, Cortes S, Rahtu E, et\u00a0al. PIVO: probabilistic inertial-visual odometry for occlusion-robust navigation. In: Proceedings of the IEEE Winter Conference on Applications of Computer Vision (WACV). 2018. p.\u00a0616\u2013625.","DOI":"10.1109\/WACV.2018.00073"},{"key":"CIT0020","unstructured":"Zhang Z, Rebecq H, Forster C, et\u00a0al. Benefit of large field-of-view cameras for visual odometry. In: Proceedings of the 2016 IEEE International Conference on Robotics and Automation (ICRA). 2016. p.\u00a0801\u2013808."},{"key":"CIT0021","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2016.2623335"},{"key":"CIT0022","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2018.2855443"},{"key":"CIT0023","doi-asserted-by":"crossref","unstructured":"Pathak S, Moro A, Fujii H, et\u00a0al. 3d reconstruction of structures using spherical cameras with small motion. In: Proceedings of the 2016 16th International Conference on Control, Automation and Systems (ICCAS). 2016. p.\u00a0117\u2013122.","DOI":"10.1109\/ICCAS.2016.7832307"},{"key":"CIT0024","doi-asserted-by":"crossref","unstructured":"Da Silveira TL, Dal'Aqua LP, Jung CR. Indoor depth estimation from single spherical images. In: Proceedings of the 2018 25th IEEE International Conference on Image Processing (ICIP). 2018. p.\u00a02935\u20132939.","DOI":"10.1109\/ICIP.2018.8451769"},{"key":"CIT0025","unstructured":"Su YC, Grauman K. Learning spherical convolution for fast features from 360\u2218 imagery. In: Proceedings of the 31st Conference on Neural Information Processing Systems (NIPS). 2017. p.\u00a0529\u2013539."},{"key":"CIT0026","doi-asserted-by":"crossref","unstructured":"Khasanova R, Frossard P. Graph-based classification of omnidirectional images. In: Proceedings of the 2017 IEEE International Conference on Computer Vision Workshop (ICCVW). 2017. p.\u00a0860\u2013869.","DOI":"10.1109\/ICCVW.2017.106"},{"key":"CIT0027","doi-asserted-by":"crossref","unstructured":"Weinzaepfel P, Revaud J, Harchaoui Z, et\u00a0al. DeepFlow: large displacement optical flow with deep matching. In: Proceedings of the 2013 IEEE International Conference on Computer Vision (ICCV). 2013. p.\u00a01385\u20131392.","DOI":"10.1109\/ICCV.2013.175"},{"key":"CIT0028","doi-asserted-by":"crossref","unstructured":"Revaud J, Weinzaepfel P, Harchaoui Z, et\u00a0al. EpicFlow: edge-preserving interpolation of correspondences for optical flow. In: Proceedings of the 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 2015. p.\u00a01164\u20131172.","DOI":"10.1109\/CVPR.2015.7298720"},{"key":"CIT0029","doi-asserted-by":"crossref","unstructured":"Wulff J, Sevilla-Lara L, Black MJ. Optical flow in mostly rigid scenes. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 2017. p.\u00a04671\u20134680.","DOI":"10.1109\/CVPR.2017.731"},{"key":"CIT0030","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2015.2505717"},{"key":"CIT0031","doi-asserted-by":"crossref","unstructured":"Mayer N, Ilg E, Hausser P, et\u00a0al. A large dataset to train convolutional networks for disparity, optical flow, and scene flow estimation. In: Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 2016.","DOI":"10.1109\/CVPR.2016.438"},{"key":"CIT0032","doi-asserted-by":"crossref","unstructured":"Guo F, He Y, Guan L. Deep camera pose regression using motion vectors. In: Proceedings of the 25th IEEE International Conference on Image Processing (ICIP). 2018. p.\u00a04073\u20134077.","DOI":"10.1109\/ICIP.2018.8451260"},{"key":"CIT0033","doi-asserted-by":"crossref","unstructured":"Hermes C, Einhaus J, Hahn M, et\u00a0al. Vehicle tracking and motion prediction in complex urban scenarios. In: 2010 IEEE Intelligent Vehicles Symposium. 2010. p.\u00a026\u201333.","DOI":"10.1109\/IVS.2010.5548014"},{"key":"CIT0034","doi-asserted-by":"crossref","unstructured":"Walker J, Gupta A, Hebert M. Dense optical flow prediction from a static image. In: Proceedings of the 2015 IEEE International Conference on Computer Vision (ICCV). 2015.","DOI":"10.1109\/ICCV.2015.281"},{"key":"CIT0035","doi-asserted-by":"crossref","unstructured":"Pathak S, Moro A, Yamashita A, et\u00a0al. A decoupled virtual camera using spherical optical flow. In: Proceedings of the 2016 IEEE International Conference on image Processing (ICIP). 2016. p.\u00a04488\u20134492.","DOI":"10.1109\/ICIP.2016.7533209"},{"key":"CIT0036","doi-asserted-by":"crossref","unstructured":"Zhou T, Brown M, Snavely N, et\u00a0al. Unsupervised learning of depth and ego-motion from video. In: Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 2017. p.\u00a06612\u20136619.","DOI":"10.1109\/CVPR.2017.700"},{"key":"CIT0037","doi-asserted-by":"crossref","unstructured":"Godard C, Mac Aodha O, Firman M, et\u00a0al. Digging into self-supervised monocular depth prediction. In: Proceedings of the 2019 IEEE International Conference on Computer Vision (ICCV). 2019. p.\u00a03828\u20133838.","DOI":"10.1109\/ICCV.2019.00393"},{"key":"CIT0038","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.2977109"},{"key":"CIT0039","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2926350"},{"key":"CIT0040","doi-asserted-by":"crossref","unstructured":"Kendall A, Grimes M, Cipolla R. Posenet: a convolutional network for real-time 6-dof camera relocalization. In: Proceedings of the 2015 IEEE International Conference on Computer Vision (ICCV). 2015. p.\u00a02938\u20132946.","DOI":"10.1109\/ICCV.2015.336"},{"key":"CIT0041","doi-asserted-by":"crossref","unstructured":"Mahendran S, Ali H, Vidal R. 3D pose regression using convolutional neural networks. In: Proceedings of the 2017 IEEE International Conference on Computer vision Workshops (ICCVW). 2017. p.\u00a02174\u20132182.","DOI":"10.1109\/ICCVW.2017.254"},{"key":"CIT0042","unstructured":"Gluckman J, Nayar SK. Ego-motion and omnidirectional cameras. In: Proceedings of the Sixth International Conference on Computer Vision. 1998. p.\u00a0999\u20131005."},{"key":"CIT0043","unstructured":"Ioffe S, Szegedy C. Batch Normalization: accelerating deep network training by reducing internal covariate shift. In: Proceedings of the 32nd International Conference on Machine Learning (icml). Vol. 37. 2015. p.\u00a0448\u2013456."},{"key":"CIT0044","unstructured":"Nair V, Hinton GE. Rectified linear units improve restricted boltzmann machines. In: Proceedings of the 27th International Conference on Machine Learning (ICML). 2010. p.\u00a0807\u2013814."},{"key":"CIT0045","unstructured":"Blender.org. 2020 [cited 2020 March 10]. Available from: https:\/\/www.blender.org\/."},{"key":"CIT0046","unstructured":"Kingma DP, Ba J. Adam: a method for stochastic optimization. In: Proceedings of the 3rd International Conference on Learning Representations (ICLR). 2015."},{"key":"CIT0047","doi-asserted-by":"crossref","unstructured":"Butler DJ, Wulff J, Stanley GB, et\u00a0al. A naturalistic open source movie for optical flow evaluation. In: Proceedings of the 12th European Conference on Computer Vision (ECCV). 2012. p.\u00a0611\u2013625.","DOI":"10.1007\/978-3-642-33783-3_44"},{"key":"CIT0048","unstructured":"Turbosquid: Royalty free license, all extended uses. 2020 [cited 2020 March 10]. Available from https:\/\/blog.turbosquid.com\/royalty-free-license\/."}],"container-title":["Advanced Robotics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.tandfonline.com\/doi\/pdf\/10.1080\/01691864.2020.1857305","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,3]],"date-time":"2022-12-03T23:32:50Z","timestamp":1670110370000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.tandfonline.com\/doi\/full\/10.1080\/01691864.2020.1857305"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,12,9]]},"references-count":48,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2021,1,17]]}},"alternative-id":["10.1080\/01691864.2020.1857305"],"URL":"https:\/\/doi.org\/10.1080\/01691864.2020.1857305","relation":{},"ISSN":["0169-1864","1568-5535"],"issn-type":[{"type":"print","value":"0169-1864"},{"type":"electronic","value":"1568-5535"}],"subject":[],"published":{"date-parts":[[2020,12,9]]},"assertion":[{"value":"The publishing and review policy for this title is described in its Aims & Scope.","order":1,"name":"peerreview_statement","label":"Peer Review Statement"},{"value":"http:\/\/www.tandfonline.com\/action\/journalInformation?show=aimsScope&journalCode=tadr20","URL":"http:\/\/www.tandfonline.com\/action\/journalInformation?show=aimsScope&journalCode=tadr20","order":2,"name":"aims_and_scope_url","label":"Aim & Scope"},{"value":"2020-03-27","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2020-10-11","order":1,"name":"revised","label":"Revised","group":{"name":"publication_history","label":"Publication History"}},{"value":"2020-11-08","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2020-12-09","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}