{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,7]],"date-time":"2026-03-07T18:51:57Z","timestamp":1772909517415,"version":"3.50.1"},"publisher-location":"Cham","reference-count":33,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030208721","type":"print"},{"value":"9783030208738","type":"electronic"}],"license":[{"start":{"date-parts":[[2019,1,1]],"date-time":"2019-01-01T00:00:00Z","timestamp":1546300800000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2019]]},"DOI":"10.1007\/978-3-030-20873-8_4","type":"book-chapter","created":{"date-parts":[[2019,5,25]],"date-time":"2019-05-25T16:32:03Z","timestamp":1558801923000},"page":"53-68","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":33,"title":["Self-supervised Learning of Depth and Camera Motion from 360 $$^\\circ $$ Videos"],"prefix":"10.1007","author":[{"given":"Fu-En","family":"Wang","sequence":"first","affiliation":[]},{"given":"Hou-Ning","family":"Hu","sequence":"additional","affiliation":[]},{"given":"Hsien-Tzu","family":"Cheng","sequence":"additional","affiliation":[]},{"given":"Juan-Ting","family":"Lin","sequence":"additional","affiliation":[]},{"given":"Shang-Ta","family":"Yang","sequence":"additional","affiliation":[]},{"given":"Meng-Li","family":"Shih","sequence":"additional","affiliation":[]},{"given":"Hung-Kuo","family":"Chu","sequence":"additional","affiliation":[]},{"given":"Min","family":"Sun","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2019,5,26]]},"reference":[{"key":"4_CR1","doi-asserted-by":"crossref","unstructured":"Byravan, A., Fox, D.: SE3-nets: learning rigid body motion using deep neural networks. In: 2017 IEEE International Conference on Robotics and Automation (ICRA), pp. 173\u2013180. IEEE (2017)","DOI":"10.1109\/ICRA.2017.7989023"},{"key":"4_CR2","doi-asserted-by":"crossref","unstructured":"Caruso, D., Engel, J., Cremers, D.: Large-scale direct slam for omnidirectional cameras. In: 2015 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 141\u2013148. IEEE (2015)","DOI":"10.1109\/IROS.2015.7353366"},{"key":"4_CR3","unstructured":"Chang, P., Hebert, M.: Omni-directional structure from motion. In: Proceedings of the 2000 IEEE Workshop on Omnidirectional Vision, pp. 127\u2013133 (2000)"},{"key":"4_CR4","doi-asserted-by":"crossref","unstructured":"Cheng, H.T., Chao, C.H., Dong, J.D., Wen, H.K., Liu, T.L., Sun, M.: Cube padding for weakly-supervised saliency prediction in 360\n                      \n                        \n                      \n                      $$^\\circ $$\n                     videos. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 2018","DOI":"10.1109\/CVPR.2018.00154"},{"key":"4_CR5","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"834","DOI":"10.1007\/978-3-319-10605-2_54","volume-title":"Computer Vision \u2013 ECCV 2014","author":"J Engel","year":"2014","unstructured":"Engel, J., Sch\u00f6ps, T., Cremers, D.: LSD-SLAM: large-scale direct monocular SLAM. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8690, pp. 834\u2013849. Springer, Cham (2014). \n                      https:\/\/doi.org\/10.1007\/978-3-319-10605-2_54"},{"key":"4_CR6","doi-asserted-by":"crossref","unstructured":"Flynn, J., Neulander, I., Philbin, J., Snavely, N.: Deepstereo: learning to predict new views from the world\u2019s imagery. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5515\u20135524 (2016)","DOI":"10.1109\/CVPR.2016.595"},{"key":"4_CR7","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"740","DOI":"10.1007\/978-3-319-46484-8_45","volume-title":"Computer Vision \u2013 ECCV 2016","author":"R Garg","year":"2016","unstructured":"Garg, R., B.G., V.K., Carneiro, G., Reid, I.: Unsupervised CNN for single view depth estimation: geometry to the rescue. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9912, pp. 740\u2013756. Springer, Cham (2016). \n                      https:\/\/doi.org\/10.1007\/978-3-319-46484-8_45"},{"key":"4_CR8","doi-asserted-by":"crossref","unstructured":"Godard, C., Mac Aodha, O., Brostow, G.J.: Unsupervised monocular depth estimation with left-right consistency. In: CVPR, vol. 2, p. 7 (2017)","DOI":"10.1109\/CVPR.2017.699"},{"issue":"2","key":"4_CR9","doi-asserted-by":"publisher","first-page":"711","DOI":"10.1109\/TIP.2016.2621662","volume":"26","author":"H Guan","year":"2017","unstructured":"Guan, H., Smith, W.A.P.: Structure-from-motion in spherical video using the von mises-fisher distribution. IEEE Trans. Image Process. 26(2), 711\u2013723 (2017)","journal-title":"IEEE Trans. Image Process."},{"key":"4_CR10","doi-asserted-by":"publisher","first-page":"14","DOI":"10.1016\/j.imavis.2017.07.003","volume":"68","author":"C H\u00e4ne","year":"2017","unstructured":"H\u00e4ne, C., et al.: 3D visual perception for self-driving cars using a multi-camera system: calibration, mapping, localization, and obstacle detection. Image Vis. Comput. (IMAVIS) 68, 14\u201327 (2017). Special Issue \u201cAutomotive Vision\u201d","journal-title":"Image Vis. Comput. (IMAVIS)"},{"key":"4_CR11","doi-asserted-by":"crossref","unstructured":"Hu, H.N., Lin, Y.C., Liu, M.Y., Cheng, H.T., Chang, Y.J., Sun, M.: Deep 360 pilot: learning a deep agent for piloting through 360\n                      \n                        \n                      \n                      $$^\\circ $$\n                     sports videos. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.153"},{"key":"4_CR12","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"156","DOI":"10.1007\/978-3-319-46487-9_10","volume-title":"Computer Vision \u2013 ECCV 2016","author":"S Im","year":"2016","unstructured":"Im, S., Ha, H., Rameau, F., Jeon, H.-G., Choe, G., Kweon, I.S.: All-around depth from small motion with a spherical panoramic camera. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9907, pp. 156\u2013172. Springer, Cham (2016). \n                      https:\/\/doi.org\/10.1007\/978-3-319-46487-9_10"},{"key":"4_CR13","doi-asserted-by":"crossref","unstructured":"Kangni, F., Laganiere, R.: Orientation and pose recovery from spherical panoramas. In: 2007 IEEE 11th International Conference on Computer Vision, pp. 1\u20138, October 2007","DOI":"10.1109\/ICCV.2007.4409198"},{"key":"4_CR14","doi-asserted-by":"publisher","first-page":"477","DOI":"10.3390\/s16040477","volume":"16","author":"A Kos","year":"2016","unstructured":"Kos, A., Tomazic, S., Umek, A.: Evaluation of smartphone inertial sensor performance for cross-platform mobile applications. Sensors 16, 477 (2016)","journal-title":"Sensors"},{"issue":"9","key":"4_CR15","first-page":"2610","volume":"24","author":"WS Lai","year":"2017","unstructured":"Lai, W.S., Huang, Y., Joshi, N., Buehler, C., Yang, M.H., Kang, S.B.: Semantic-driven generation of hyperlapse from 360\n                      \n                        \n                      \n                      $$^\\circ $$\n                     video. TVCG 24(9), 2610\u20132621 (2017)","journal-title":"TVCG"},{"key":"4_CR16","doi-asserted-by":"crossref","unstructured":"Laina, I., Rupprecht, C., Belagiannis, V., Tombari, F., Navab, N.: Deeper depth prediction with fully convolutional residual networks. In: 2016 Fourth International Conference on 3D Vision (3DV), pp. 239\u2013248. IEEE (2016)","DOI":"10.1109\/3DV.2016.32"},{"key":"4_CR17","doi-asserted-by":"crossref","unstructured":"Lin, Y.C., Chang, Y.J., Hu, H.N., Cheng, H.T., Huang, C.W., Sun, M.: Tell me where to look: investigating ways for assisting focus in 360\n                      \n                        \n                      \n                      $$^{\\circ }$$\n                     video. In: CHI (2017)","DOI":"10.1145\/3025453.3025757"},{"key":"4_CR18","doi-asserted-by":"crossref","unstructured":"Mahjourian, R., Wicke, M., Angelova, A.: Unsupervised learning of depth and ego-motion from monocular video using 3D geometric constraints. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 2018","DOI":"10.1109\/CVPR.2018.00594"},{"key":"4_CR19","doi-asserted-by":"crossref","unstructured":"Mayer, N., et al.: A large dataset to train convolutional networks for disparity, optical flow, and scene flow estimation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4040\u20134048 (2016)","DOI":"10.1109\/CVPR.2016.438"},{"key":"4_CR20","doi-asserted-by":"crossref","unstructured":"Pagani, A., Stricker, D.: Structure from motion using full spherical panoramic cameras. In: 2011 IEEE International Conference on Computer Vision Workshops (ICCV Workshops), pp. 375\u2013382, November 2011","DOI":"10.1109\/ICCVW.2011.6130266"},{"key":"4_CR21","unstructured":"Paszke, A., Chintala, S.: Pytorch. \n                      https:\/\/github.com\/apaszke\/pytorch-dist"},{"key":"4_CR22","doi-asserted-by":"crossref","unstructured":"Pathak, S., Moro, A., Fujii, H., Yamashita, A., Asama, H.: 3D reconstruction of structures using spherical cameras with small motion. In: 2016 16th International Conference on Control, Automation and Systems (ICCAS), pp. 117\u2013122, October 2016","DOI":"10.1109\/ICCAS.2016.7832307"},{"key":"4_CR23","doi-asserted-by":"crossref","unstructured":"Sch\u00f6nbein, M., Geiger, A.: Omnidirectional 3D reconstruction in augmented manhattan worlds. In: 2014 IEEE\/RSJ International Conference on Intelligent Robots and Systems, pp. 716\u2013723, September 2014","DOI":"10.1109\/IROS.2014.6942637"},{"key":"4_CR24","doi-asserted-by":"crossref","unstructured":"Song, S., Yu, F., Zeng, A., Chang, A.X., Savva, M., Funkhouser, T.: Semantic scene completion from a single depth image. In: IEEE Conference on Computer Vision and Pattern Recognition (2017)","DOI":"10.1109\/CVPR.2017.28"},{"key":"4_CR25","unstructured":"Su, Y.C., Grauman, K.: Learning spherical convolution for fast features from 360\n                      \n                        \n                      \n                      $$^{\\circ }$$\n                     imagery. In: NIPS (2017)"},{"key":"4_CR26","doi-asserted-by":"crossref","unstructured":"Su, Y.C., Grauman, K.: Making 360\n                      \n                        \n                      \n                      $$^{\\circ }$$\n                     video watchable in 2D: learning videography for click free viewing. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.150"},{"key":"4_CR27","unstructured":"Su, Y.C., Jayaraman, D., Grauman, K.: Pano2Vid: automatic cinematography for watching 360\n                      \n                        \n                      \n                      $$^{\\circ }$$\n                     videos. In: ACCV (2016)"},{"key":"4_CR28","doi-asserted-by":"crossref","unstructured":"Tateno, K., Tombari, F., Laina, I., Navab, N.: CNN-SLAM: real-time dense monocular slam with learned depth prediction. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2017)","DOI":"10.1109\/CVPR.2017.695"},{"key":"4_CR29","unstructured":"Vijayanarasimhan, S., Ricco, S., Schmid, C., Sukthankar, R., Fragkiadaki, K.: SfM-net: learning of structure and motion from video. CoRR abs\/1704.07804 (2017)"},{"key":"4_CR30","doi-asserted-by":"crossref","unstructured":"Wang, C., Miguel Buenaposada, J., Zhu, R., Lucey, S.: Learning depth from monocular videos using direct methods. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 2018","DOI":"10.1109\/CVPR.2018.00216"},{"key":"4_CR31","unstructured":"Wang, F.E., et al.: Technical report of self-supervised 360 depth (2018). \n                      https:\/\/aliensunmin.github.io\/project\/360-depth\/"},{"key":"4_CR32","doi-asserted-by":"crossref","unstructured":"Wang, T.H., Huang, H.J., Lin, J.T., Hu, C.W., Zeng, K.H., Sun, M.: Omnidirectional CNN for Visual Place Recognition and Navigation. CoRR abs\/1803.04228v1 (2018)","DOI":"10.1109\/ICRA.2018.8463173"},{"key":"4_CR33","doi-asserted-by":"crossref","unstructured":"Zhou, T., Brown, M., Snavely, N., Lowe, D.G.: Unsupervised learning of depth and ego-motion from video. In: CVPR, vol. 2, p. 7 (2017)","DOI":"10.1109\/CVPR.2017.700"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ACCV 2018"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-20873-8_4","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,5,26]],"date-time":"2019-05-26T02:43:06Z","timestamp":1558838586000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-030-20873-8_4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019]]},"ISBN":["9783030208721","9783030208738"],"references-count":33,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-20873-8_4","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019]]},"assertion":[{"value":"26 May 2019","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ACCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Asian Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Perth, WA","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Australia","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2018","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2 December 2018","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"6 December 2018","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"14","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"accv2018","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/accv2018.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}},{"value":"Microsoft CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}},{"value":"979","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}},{"value":"274","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}},{"value":"28% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}},{"value":"3","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}},{"value":"2.7","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}},{"value":"No","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}}]}}