{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T15:24:30Z","timestamp":1778081070917,"version":"3.51.4"},"publisher-location":"Cham","reference-count":35,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030873608","type":"print"},{"value":"9783030873615","type":"electronic"}],"license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"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":[[2021]]},"DOI":"10.1007\/978-3-030-87361-5_38","type":"book-chapter","created":{"date-parts":[[2021,9,29]],"date-time":"2021-09-29T23:54:11Z","timestamp":1632959651000},"page":"465-477","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Semantic and Optical Flow Guided Self-supervised Monocular Depth and Ego-Motion Estimation"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1768-7465","authenticated-orcid":false,"given":"Jiaojiao","family":"Fang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9149-4576","authenticated-orcid":false,"given":"Guizhong","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2021,9,30]]},"reference":[{"key":"38_CR1","doi-asserted-by":"crossref","unstructured":"Chen, P., Liu, A.H., Liu, Y., Wang, Y.F.: Towards scene understanding: Unsupervised monocular depth estimation with semantic-aware representation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2624\u20132632 (2019)","DOI":"10.1109\/CVPR.2019.00273"},{"key":"38_CR2","doi-asserted-by":"crossref","unstructured":"Chen, Y., Schmid, C., Sminchisescu, C.: Self-supervised learning with geometric constraints in monocular video: connecting flow, depth, and camera. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 7063\u20137072 (2019)","DOI":"10.1109\/ICCV.2019.00716"},{"key":"38_CR3","doi-asserted-by":"crossref","unstructured":"Zhan, H., Weerasekera, C.S., Bian, J., Reid, I.: Visual odometry revisited: What should be learnt?. In: IEEE International Conference on Robotics and Automation, pp. 4203\u20134210 (2020)","DOI":"10.1109\/ICRA40945.2020.9197374"},{"key":"38_CR4","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, pp. 3213\u20133223 (2016)","DOI":"10.1109\/CVPR.2016.350"},{"key":"38_CR5","unstructured":"Eigen, D., Puhrsch, C., Fergus, R.: Depth map prediction from a single image using a multi-scale deep network. In: Advances in Neural Information Processing systems, pp. 2366\u20132374 (2014)"},{"key":"38_CR6","doi-asserted-by":"crossref","unstructured":"Fan, L., Huang, W., Gan, C., Ermon, S., Gong, B., Huang, J.: End-to-end learning of motion representation for video understanding. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6016\u20136025 (2018)","DOI":"10.1109\/CVPR.2018.00630"},{"key":"38_CR7","doi-asserted-by":"crossref","unstructured":"Garg, R., Kumar, B,G.V., Carneiro, G., Reid, I.: Unsupervised CNN for single view depth estimation: geometry to the rescue. In: European Conference on Computer Vision, pp. 740\u2013756 (2016)","DOI":"10.1007\/978-3-319-46484-8_45"},{"key":"38_CR8","doi-asserted-by":"crossref","unstructured":"Geiger, A., Lenz, P., Urtasun, R.: Are we ready for autonomous driving? The kitti vision benchmark suite. In: 2012 IEEE Conference on Computer Vision and Pattern Recognition, pp. 3354\u20133361 (2012)","DOI":"10.1109\/CVPR.2012.6248074"},{"key":"38_CR9","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":"38_CR10","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 International Conference on Computer Vision, pp. 3828\u20133838 (2019)","DOI":"10.1109\/ICCV.2019.00393"},{"key":"38_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: IEEE\/CVF Conference on Computer Vision and Pattern Recognition (2020)","DOI":"10.1109\/CVPR42600.2020.00256"},{"key":"38_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: International Conference on Learning Representations (2020)","DOI":"10.1109\/CVPR42600.2020.00256"},{"key":"38_CR13","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":"38_CR14","unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)"},{"key":"38_CR15","doi-asserted-by":"crossref","unstructured":"Laina, I., Rupprecht, C., Belagiannis, V., Tombari, F., Navab, N.: Deeper depth prediction with fully convolutional residual networks. In: International Conference on 3D Vision, pp. 239\u2013248 (2016)","DOI":"10.1109\/3DV.2016.32"},{"key":"38_CR16","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: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5667\u20135675 (2018)","DOI":"10.1109\/CVPR.2018.00594"},{"key":"38_CR17","unstructured":"Paszke, A., et al.: PyTorch: An imperative style, high-performance deep learning library. In: Proceedings of NeurIPS, Vancouver, BC, Canada, pp. 8024\u20138035 (2019)"},{"key":"38_CR18","doi-asserted-by":"crossref","unstructured":"Poggi, M., Aleotti, F., Tosi, F., Mattoccia, S.: On the uncertainty of self-supervised monocular depth estimation. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2020)","DOI":"10.1109\/CVPR42600.2020.00329"},{"key":"38_CR19","doi-asserted-by":"crossref","unstructured":"Ranjan, A., et al.: Competitive collaboration: Joint unsupervised learning of depth, camera motion, optical flow and motion segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 12240\u201312249 (2019)","DOI":"10.1109\/CVPR.2019.01252"},{"issue":"3","key":"38_CR20","doi-asserted-by":"publisher","first-page":"211","DOI":"10.1007\/s11263-015-0816-y","volume":"115","author":"O Russakovsky","year":"2015","unstructured":"Russakovsky, O., et al.: Imagenet large scale visual recognition challenge. Int. J. Comput. Vis. 115(3), 211\u2013252 (2015)","journal-title":"Int. J. Comput. Vis."},{"issue":"5","key":"38_CR21","doi-asserted-by":"publisher","first-page":"824","DOI":"10.1109\/TPAMI.2008.132","volume":"31","author":"A Saxena","year":"2009","unstructured":"Saxena, A., Sun, M., Ng, A.Y.: Make3D: learning 3D scene structure from a single still image. IEEE Trans. Pattern Anal. Mach. Intell. 31(5), 824\u2013840 (2009)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"38_CR22","doi-asserted-by":"crossref","unstructured":"Yin, Z., Shi, J.: 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 (2018)","DOI":"10.1109\/CVPR.2018.00212"},{"key":"38_CR23","doi-asserted-by":"crossref","unstructured":"Zhou, T., Brown, M., Snavely, N., Lowe, D.G.: Unsupervised learning of depth and ego-motion from video. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1851\u20131858 (2017)","DOI":"10.1109\/CVPR.2017.700"},{"key":"38_CR24","doi-asserted-by":"crossref","unstructured":"Wang, G., Wang, H., Liu, Y., Chen, W.: Unsupervised learning of monocular depth and ego-motion using multiple masks. In: IEEE 2019 International Conference on Robotics and Automation (ICRA), pp. 4724\u20134730 (2019)","DOI":"10.1109\/ICRA.2019.8793622"},{"key":"38_CR25","first-page":"8001","volume":"33","author":"V Casser","year":"2019","unstructured":"Casser, V., Pirk, S., Mahjourian, R., Angelova, A.: Depth prediction without the sensors: leveraging structure for unsupervised learning from monocular videos. Proc. AAAI Conf. Artif. Intell. 33, 8001\u20138008 (2019)","journal-title":"Proc. AAAI Conf. Artif. Intell."},{"key":"38_CR26","unstructured":"Bian, J., et al.: Unsupervised scale-consistent depth and ego-motion learning from monocular video. Adv. Neural Inf. Process. Syst. 35\u201345 (2019)"},{"key":"38_CR27","unstructured":"Choi, J., Jung, D., Lee, D., Kim, C.: Safenet: Self-supervised monocular depth estimation with semantic-aware feature extraction. In: Workshops at the 34th Conference on Neural Information Processing Systems (2020)"},{"key":"38_CR28","doi-asserted-by":"crossref","unstructured":"Li, R., He, X., Zhu, Y., Li, X., Sun, J., Zhang, Y.: Enhancing self-supervised monocular depth estimation via incorporating robust constraints. In: Proceedings of the 28th ACM International Conference on Multimedia, pp. 3108\u20133117 (2020)","DOI":"10.1145\/3394171.3413706"},{"key":"38_CR29","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 (2017)","DOI":"10.1109\/3DV.2017.00012"},{"key":"38_CR30","doi-asserted-by":"crossref","unstructured":"Klingner, M., Termohlen, J., Mikolajczyk, J., Fingscheidt, T.: Self-supervised monocular depth estimation: Solving the dynamic object problem by semantic guidance. In: European Conference on Computer Vision, (2020)","DOI":"10.1007\/978-3-030-58565-5_35"},{"key":"38_CR31","doi-asserted-by":"crossref","unstructured":"Meng, Y., et al.: SIGNet: semantic instance aided unsupervised 3D geometry perception. In: Proceedings of CVPR, Long Beach, CA, USA, pp. 9810\u20139820, June 2019","DOI":"10.1109\/CVPR.2019.01004"},{"key":"38_CR32","doi-asserted-by":"crossref","unstructured":"Shen, T., Luo, Z., Zhou, L., et al.: Beyond photometric loss for self-supervised ego-motion estimation. In: International Conference on Robotics and Automation, pp. 6359\u20136365 (2019)","DOI":"10.1109\/ICRA.2019.8793479"},{"key":"38_CR33","doi-asserted-by":"crossref","unstructured":"Xue, F., Zhuo, G., Huang, Z., Fu, W., Wu, Z., Ang, Jr.: Toward hierarchical self-supervised monocular absolute depth estimation for autonomous driving applications. In: IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS) (2020)","DOI":"10.1109\/IROS45743.2020.9340802"},{"key":"38_CR34","doi-asserted-by":"crossref","unstructured":"Zach, C., Pock, T., Bischof, H.: A duality based approach for realtime TV-L1 optical flow. Pattern Recogn. 214\u2013223 (2007)","DOI":"10.1007\/978-3-540-74936-3_22"},{"key":"38_CR35","doi-asserted-by":"crossref","unstructured":"Schonberger, J.-L., Frahm, J.-M.: Structure-from-motion revisited. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4104\u20134113 (2016)","DOI":"10.1109\/CVPR.2016.445"}],"container-title":["Lecture Notes in Computer Science","Image and Graphics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-87361-5_38","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,10]],"date-time":"2023-01-10T19:54:16Z","timestamp":1673380456000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-87361-5_38"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"ISBN":["9783030873608","9783030873615"],"references-count":35,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-87361-5_38","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021]]},"assertion":[{"value":"30 September 2021","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICIG","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Image and Graphics","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Haikou","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2021","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"6 August 2021","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 August 2021","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"11","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icig2021","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/icig2021.csig.org.cn\/","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":"421","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":"198","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":"47% - 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","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","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)"}},{"value":"Conference was postponed due to the COVID19 pandemic.","order":10,"name":"additional_info_on_review_process","label":"Additional Info on Review Process","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}