{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T12:29:05Z","timestamp":1782908945011,"version":"3.54.5"},"publisher-location":"Cham","reference-count":38,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031198236","type":"print"},{"value":"9783031198243","type":"electronic"}],"license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022]]},"DOI":"10.1007\/978-3-031-19824-3_14","type":"book-chapter","created":{"date-parts":[[2022,11,10]],"date-time":"2022-11-10T21:14:32Z","timestamp":1668114872000},"page":"228-244","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":79,"title":["Disentangling Object Motion and Occlusion for Unsupervised Multi-frame Monocular Depth"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0037-3697","authenticated-orcid":false,"given":"Ziyue","family":"Feng","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Liang","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Longlong","family":"Jing","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Haiyan","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"YingLi","family":"Tian","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bing","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2022,11,11]]},"reference":[{"key":"14_CR1","doi-asserted-by":"crossref","unstructured":"Casser, V., Pirk, S., Mahjourian, R., Angelova, A.: Depth prediction without the sensors: leveraging structure for unsupervised learning from monocular videos. In: AAAI (2019)","DOI":"10.1609\/aaai.v33i01.33018001"},{"key":"14_CR2","doi-asserted-by":"crossref","unstructured":"Casser, V., Pirk, S., Mahjourian, R., Angelova, A.: Unsupervised monocular depth and ego-motion learning with structure and semantics. In: CVPR Workshops (2019)","DOI":"10.1109\/CVPRW.2019.00051"},{"key":"14_CR3","doi-asserted-by":"crossref","unstructured":"Cordts, M., et al.: The cityscapes dataset for semantic urban scene understanding. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2016)","DOI":"10.1109\/CVPR.2016.350"},{"key":"14_CR4","doi-asserted-by":"crossref","unstructured":"CS Kumar, A., Bhandarkar, S.M., Prasad, M.: Depthnet: a recurrent neural network architecture for monocular depth prediction. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops, pp. 283\u2013291 (2018)","DOI":"10.1109\/CVPRW.2018.00066"},{"key":"14_CR5","doi-asserted-by":"crossref","unstructured":"Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., Fei-Fei, L.: Imagenet: a large-scale hierarchical image database. In: 2009 IEEE Conference on Computer Vision and Pattern Recognition, pp. 248\u2013255. IEEE (2009)","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"14_CR6","doi-asserted-by":"crossref","unstructured":"Eigen, D., Fergus, R.: Predicting depth, surface normals and semantic labels with a common multi-scale convolutional architecture. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2650\u20132658 (2015)","DOI":"10.1109\/ICCV.2015.304"},{"key":"14_CR7","unstructured":"Gao, F., Yu, J., Shen, H., Wang, Y., Yang, H.: Attentional separation-and-aggregation network for self-supervised depth-pose learning in dynamic scenes. arXiv preprint arXiv:2011.09369 (2020)"},{"key":"14_CR8","doi-asserted-by":"crossref","unstructured":"Godard, C., Mac Aodha, O., Brostow, G.J.: Unsupervised monocular depth estimation with left-right consistency. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 270\u2013279 (2017)","DOI":"10.1109\/CVPR.2017.699"},{"key":"14_CR9","doi-asserted-by":"crossref","unstructured":"Godard, C., Mac Aodha, O., Firman, M., Brostow, G.J.: Digging into self-supervised monocular depth estimation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 3828\u20133838 (2019)","DOI":"10.1109\/ICCV.2019.00393"},{"key":"14_CR10","doi-asserted-by":"crossref","unstructured":"Gordon, A., Li, H., Jonschkowski, R., Angelova, A.: Depth from videos in the wild: unsupervised monocular depth learning from unknown cameras. In: ICCV (2019)","DOI":"10.1109\/ICCV.2019.00907"},{"key":"14_CR11","doi-asserted-by":"crossref","unstructured":"Guizilini, V., Ambrus, R., Pillai, S., Raventos, A., Gaidon, A.: 3D packing for self-supervised monocular depth estimation. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.00256"},{"key":"14_CR12","doi-asserted-by":"crossref","unstructured":"Guizilini, V., Hou, R., Li, J., Ambrus, R., Gaidon, A.: Semantically-guided representation learning for self-supervised monocular depth. In: ICLR (2020)","DOI":"10.1109\/CVPR42600.2020.00256"},{"key":"14_CR13","doi-asserted-by":"crossref","unstructured":"Ha, H., Im, S., Park, J., Jeon, H.G., Kweon, I.S.: High-quality depth from uncalibrated small motion clip. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5413\u20135421 (2016)","DOI":"10.1109\/CVPR.2016.584"},{"key":"14_CR14","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"14_CR15","doi-asserted-by":"crossref","unstructured":"Johnston, A., Carneiro, G.: Self-supervised monocular trained depth estimation using self-attention and discrete disparity volume. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.00481"},{"key":"14_CR16","unstructured":"Joshi, N., Zitnick, C.L.: Micro-baseline stereo. Microsoft Research Technical Report (2014)"},{"key":"14_CR17","unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)"},{"key":"14_CR18","doi-asserted-by":"publisher","unstructured":"Klingner, M., Term\u00f6hlen, J.-A., Mikolajczyk, J., Fingscheidt, T.: Self-supervised monocular depth estimation: solving the dynamic object problem by semantic guidance. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12365, pp. 582\u2013600. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58565-5_35","DOI":"10.1007\/978-3-030-58565-5_35"},{"key":"14_CR19","doi-asserted-by":"crossref","unstructured":"Lee, S., Im, S., Lin, S., Kweon, I.S.: Learning monocular depth in dynamic scenes via instance-aware projection consistency. In: 35th AAAI Conference on Artificial Intelligence\/33rd Conference on Innovative Applications of Artificial Intelligence\/11th Symposium on Educational Advances in Artificial Intelligence, pp. 1863\u20131872. Assoc Advancement Artificial Intelligence (2021)","DOI":"10.1609\/aaai.v35i3.16281"},{"key":"14_CR20","doi-asserted-by":"crossref","unstructured":"Lee, S., Rameau, F., Pan, F., Kweon, I.S.: Attentive and contrastive learning for joint depth and motion field estimation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 4862\u20134871 (2021)","DOI":"10.1109\/ICCV48922.2021.00482"},{"key":"14_CR21","unstructured":"Li, H., Gordon, A., Zhao, H., Casser, V., Angelova, A.: Unsupervised monocular depth learning in dynamic scenes. In: CoRL (2020)"},{"key":"14_CR22","doi-asserted-by":"crossref","unstructured":"Li, Z., et al.: Learning the depths of moving people by watching frozen people. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4521\u20134530 (2019)","DOI":"10.1109\/CVPR.2019.00465"},{"key":"14_CR23","doi-asserted-by":"crossref","unstructured":"Luo, C., et al.: Every pixel counts++: joint learning of geometry and motion with 3D holistic understanding. PAMI (2019)","DOI":"10.1109\/TPAMI.2019.2930258"},{"key":"14_CR24","doi-asserted-by":"crossref","unstructured":"Menze, M., Geiger, A.: Object scene flow for autonomous vehicles. In: Conference on Computer Vision and Pattern Recognition (CVPR) (2015)","DOI":"10.1109\/CVPR.2015.7298925"},{"issue":"5","key":"14_CR25","doi-asserted-by":"publisher","first-page":"1551","DOI":"10.1007\/s11263-021-01445-z","volume":"129","author":"R Mohan","year":"2021","unstructured":"Mohan, R., Valada, A.: Efficientps: efficient panoptic segmentation. Int. J. Comput. Vis. 129(5), 1551\u20131579 (2021)","journal-title":"Int. J. Comput. Vis."},{"issue":"4","key":"14_CR26","doi-asserted-by":"publisher","first-page":"6813","DOI":"10.1109\/LRA.2020.3017478","volume":"5","author":"V Patil","year":"2020","unstructured":"Patil, V., Van Gansbeke, W., Dai, D., Van Gool, L.: Don\u2019t forget the past: recurrent depth estimation from monocular video. IEEE Robot. Autom. Lett. 5(4), 6813\u20136820 (2020)","journal-title":"IEEE Robot. Autom. Lett."},{"key":"14_CR27","doi-asserted-by":"crossref","unstructured":"Pilzer, A., Xu, D., Puscas, M.M., Ricci, E., Sebe, N.: Unsupervised adversarial depth estimation using cycled generative networks. In: 3DV (2018)","DOI":"10.1109\/3DV.2018.00073"},{"key":"14_CR28","doi-asserted-by":"crossref","unstructured":"Ranjan, A., Jampani, V., Kim, K., Sun, D., Wulff, J., Black, M.J.: Competitive collaboration: Joint unsupervised learning of depth, camera motion, optical flow and motion segmentation. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.01252"},{"key":"14_CR29","doi-asserted-by":"publisher","unstructured":"Shu, C., Yu, K., Duan, Z., Yang, K.: Feature-Metric Loss for Self-supervised Learning of Depth and Egomotion. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J-M. (eds.) ECCV 2020. LNCS, vol. 12364, pp. 572\u2013588. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58529-7_34","DOI":"10.1007\/978-3-030-58529-7_34"},{"key":"14_CR30","doi-asserted-by":"crossref","unstructured":"Uhrig, J., Schneider, N., Schneider, L., Franke, U., Brox, T., Geiger, A.: Sparsity invariant CNNS. In: International Conference on 3D Vision (3DV) (2017)","DOI":"10.1109\/3DV.2017.00012"},{"key":"14_CR31","doi-asserted-by":"crossref","unstructured":"Wang, C., Buenaposada, J.M., Zhu, R., Lucey, S.: Learning depth from monocular videos using direct methods. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2022\u20132030 (2018)","DOI":"10.1109\/CVPR.2018.00216"},{"key":"14_CR32","unstructured":"Wang, J., Zhang, G., Wu, Z., Li, X., Liu, L.: Self-supervised joint learning framework of depth estimation via implicit cues. arXiv:2006.09876 (2020)"},{"key":"14_CR33","doi-asserted-by":"crossref","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 of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5555\u20135564 (2019)","DOI":"10.1109\/CVPR.2019.00570"},{"issue":"4","key":"14_CR34","doi-asserted-by":"publisher","first-page":"600","DOI":"10.1109\/TIP.2003.819861","volume":"13","author":"Z Wang","year":"2004","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(4), 600\u2013612 (2004)","journal-title":"IEEE Trans. image Process."},{"key":"14_CR35","doi-asserted-by":"crossref","unstructured":"Watson, J., Mac Aodha, O., Prisacariu, V., Brostow, G., Firman, M.: The temporal opportunist: self-supervised multi-frame monocular depth. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 1164\u20131174 (2021)","DOI":"10.1109\/CVPR46437.2021.00122"},{"key":"14_CR36","doi-asserted-by":"crossref","unstructured":"Wimbauer, F., Yang, N., Von Stumberg, L., Zeller, N., Cremers, D.: Monorec: semi-supervised dense reconstruction in dynamic environments from a single moving camera. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 6112\u20136122 (2021)","DOI":"10.1109\/CVPR46437.2021.00605"},{"key":"14_CR37","doi-asserted-by":"crossref","unstructured":"Zhang, H., Shen, C., Li, Y., Cao, Y., Liu, Y., Yan, Y.: Exploiting temporal consistency for real-time video depth estimation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 1725\u20131734 (2019)","DOI":"10.1109\/ICCV.2019.00181"},{"issue":"1","key":"14_CR38","doi-asserted-by":"publisher","first-page":"47","DOI":"10.1109\/TCI.2016.2644865","volume":"3","author":"H Zhao","year":"2016","unstructured":"Zhao, H., Gallo, O., Frosio, I., Kautz, J.: Loss functions for image restoration with neural networks. IEEE Trans. Comput. Imaging 3(1), 47\u201357 (2016)","journal-title":"IEEE Trans. Comput. Imaging"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2022"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-19824-3_14","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,11,12]],"date-time":"2022-11-12T00:10:41Z","timestamp":1668211841000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-19824-3_14"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031198236","9783031198243"],"references-count":38,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-19824-3_14","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022]]},"assertion":[{"value":"11 November 2022","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Tel Aviv","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Israel","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2022","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23 October 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27 October 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2022.ecva.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 (provided by the conference organizers)"}},{"value":"CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"5804","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"1645","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"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 (provided by the conference organizers)"}},{"value":"3.21","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3.91","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}