{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T18:42:21Z","timestamp":1775068941348,"version":"3.50.1"},"publisher-location":"Cham","reference-count":43,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031197680","type":"print"},{"value":"9783031197697","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\/978-3-031-19769-7_6","type":"book-chapter","created":{"date-parts":[[2022,10,22]],"date-time":"2022-10-22T11:40:06Z","timestamp":1666438806000},"page":"89-105","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":20,"title":["Adaptive Co-teaching for\u00a0Unsupervised Monocular Depth Estimation"],"prefix":"10.1007","author":[{"given":"Weisong","family":"Ren","sequence":"first","affiliation":[]},{"given":"Lijun","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Yongri","family":"Piao","sequence":"additional","affiliation":[]},{"given":"Miao","family":"Zhang","sequence":"additional","affiliation":[]},{"given":"Huchuan","family":"Lu","sequence":"additional","affiliation":[]},{"given":"Ting","family":"Liu","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2022,10,23]]},"reference":[{"key":"6_CR1","first-page":"35","volume":"32","author":"J Bian","year":"2019","unstructured":"Bian, J., et al.: Unsupervised scale-consistent depth and ego-motion learning from monocular video. Adv. Neural. Inf. Process. Syst. 32, 35\u201345 (2019)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"6_CR2","doi-asserted-by":"crossref","unstructured":"Bloesch, M., Czarnowski, J., Clark, R., Leutenegger, S., Davison, A.J.: Codeslam-learning a compact, optimisable representation for dense visual slam. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2560\u20132568 (2018)","DOI":"10.1109\/CVPR.2018.00271"},{"key":"6_CR3","doi-asserted-by":"crossref","unstructured":"Bucila, C., Caruana, R., Niculescu-Mizil, A.: Model compression. In: ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD 2006) (2006)","DOI":"10.1145\/1150402.1150464"},{"key":"6_CR4","doi-asserted-by":"crossref","unstructured":"Caesar, H., et al.: nuscenes: a multimodal dataset for autonomous driving. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11621\u201311631 (2020)","DOI":"10.1109\/CVPR42600.2020.01164"},{"key":"6_CR5","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: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 33, pp. 8001\u20138008 (2019)","DOI":"10.1609\/aaai.v33i01.33018001"},{"key":"6_CR6","unstructured":"Chen, G., Choi, W., Yu, X., Han, T., Chandraker, M.: Learning efficient object detection models with knowledge distillation. Adv. Neural Inf. Process. Syst. 30 (2017)"},{"key":"6_CR7","unstructured":"Choi, J., Jung, D., Lee, D., Kim, C.: Safenet: self-supervised monocular depth estimation with semantic-aware feature extraction. In: Thirty-Fourth Conference on Neural Information Processing Systems, NIPS 2020. NeurIPS (2020)"},{"key":"6_CR8","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":"6_CR9","unstructured":"Eigen, D., Puhrsch, C., Fergus, R.: Depth map prediction from a single image using a multi-scale deep network. In: 28th Annual Conference on Neural Information Processing Systems 2014, NIPS 2014, pp. 2366\u20132374. Neural information processing systems foundation (2014)"},{"key":"6_CR10","doi-asserted-by":"crossref","unstructured":"Fan, H., Hao, S., Guibas, L.: A point set generation network for 3D object reconstruction from a single image. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2017)","DOI":"10.1109\/CVPR.2017.264"},{"key":"6_CR11","unstructured":"Fang, J., Liu, G.: Self-supervised learning of depth and ego-motion from video by alternative training and geometric constraints from 3D to 2D. arXiv preprint arXiv:2108.01980 (2021)"},{"key":"6_CR12","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). https:\/\/doi.org\/10.1007\/978-3-319-46484-8_45"},{"key":"6_CR13","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. IEEE (2012)","DOI":"10.1109\/CVPR.2012.6248074"},{"key":"6_CR14","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":"6_CR15","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":"6_CR16","doi-asserted-by":"crossref","unstructured":"Guizilini, V., Ambrus, R., Pillai, S., Raventos, A., Gaidon, A.: 3D packing for self-supervised monocular depth estimation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2485\u20132494 (2020)","DOI":"10.1109\/CVPR42600.2020.00256"},{"key":"6_CR17","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 (2019)","DOI":"10.1109\/CVPR42600.2020.00256"},{"key":"6_CR18","doi-asserted-by":"crossref","unstructured":"Gupta, S., Hoffman, J., Malik, J.: Cross modal distillation for supervision transfer. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2827\u20132836 (2016)","DOI":"10.1109\/CVPR.2016.309"},{"key":"6_CR19","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":"6_CR20","unstructured":"Hinton, G., Vinyals, O., Dean, J.: Distilling the knowledge in a neural network. arXiv preprint arXiv:1503.02531 (2015)"},{"key":"6_CR21","doi-asserted-by":"crossref","unstructured":"Janai, J., Guney, F., Ranjan, A., Black, M., Geiger, A.: Unsupervised learning of multi-frame optical flow with occlusions. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 690\u2013706 (2018)","DOI":"10.1007\/978-3-030-01270-0_42"},{"key":"6_CR22","doi-asserted-by":"crossref","unstructured":"Johnston, A., Carneiro, G.: Self-supervised monocular trained depth estimation using self-attention and discrete disparity volume. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4756\u20134765 (2020)","DOI":"10.1109\/CVPR42600.2020.00481"},{"key":"6_CR23","unstructured":"Kingma, D.P., Ba, J.: Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)"},{"key":"6_CR24","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: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 35, pp. 1863\u20131872 (2021)","DOI":"10.1609\/aaai.v35i3.16281"},{"key":"6_CR25","doi-asserted-by":"crossref","unstructured":"Li, S., Wu, X., Cao, Y., Zha, H.: Generalizing to the open world: deep visual odometry with online adaptation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 13184\u201313193 (2021)","DOI":"10.1109\/CVPR46437.2021.01298"},{"key":"6_CR26","doi-asserted-by":"crossref","unstructured":"Li, Y., Yang, J., Song, Y., Cao, L., Li, L.J.: Learning from noisy labels with distillation. In: 2017 IEEE International Conference on Computer Vision (ICCV) (2017)","DOI":"10.1109\/ICCV.2017.211"},{"key":"6_CR27","unstructured":"Lyu, X., et al.: Hr-depth: high resolution self-supervised monocular depth estimation. CoRR abs\/2012.07356 (2020)"},{"key":"6_CR28","doi-asserted-by":"crossref","unstructured":"Peng, R., Wang, R., Lai, Y., Tang, L., Cai, Y.: Excavating the potential capacity of self-supervised monocular depth estimation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 15560\u201315569 (2021)","DOI":"10.1109\/ICCV48922.2021.01527"},{"key":"6_CR29","doi-asserted-by":"crossref","unstructured":"Pilzer, A., Lathuili\u00e8re, S., Sebe, N., Ricci, E.: Refine and distill: exploiting cycle-inconsistency and knowledge distillation for unsupervised monocular depth estimation. In: 2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2020)","DOI":"10.1109\/CVPR.2019.01000"},{"key":"6_CR30","doi-asserted-by":"crossref","unstructured":"Pilzer, A., Xu, D., Puscas, M., Ricci, E., Sebe, N.: Unsupervised adversarial depth estimation using cycled generative networks. In: 2018 International Conference on 3D Vision (3DV), pp. 587\u2013595. IEEE (2018)","DOI":"10.1109\/3DV.2018.00073"},{"key":"6_CR31","doi-asserted-by":"crossref","unstructured":"Poggi, M., Aleotti, F., Tosi, F., Mattoccia, S.: On the uncertainty of self-supervised monocular depth estimation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 3227\u20133237 (2020)","DOI":"10.1109\/CVPR42600.2020.00329"},{"key":"6_CR32","doi-asserted-by":"publisher","first-page":"27","DOI":"10.1016\/j.robot.2018.08.009","volume":"109","author":"T Prucksakorn","year":"2018","unstructured":"Prucksakorn, T., Jeong, S., Chong, N.Y.: A self-trainable depth perception method from eye pursuit and motion parallax. Robot. Auton. Syst. 109, 27\u201337 (2018)","journal-title":"Robot. Auton. Syst."},{"key":"6_CR33","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"572","DOI":"10.1007\/978-3-030-58529-7_34","volume-title":"Computer Vision \u2013 ECCV 2020","author":"C Shu","year":"2020","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"},{"key":"6_CR34","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"402","DOI":"10.1007\/978-3-030-58536-5_24","volume-title":"Computer Vision \u2013 ECCV 2020","author":"Z Teed","year":"2020","unstructured":"Teed, Z., Deng, J.: RAFT: recurrent all-pairs field transforms for optical flow. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12347, pp. 402\u2013419. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58536-5_24"},{"key":"6_CR35","unstructured":"Wagstaff, B., Peretroukhin, V., Kelly, J.: Self-supervised structure-from-motion through tightly-coupled depth and egomotion networks. arXiv preprint arXiv:2106.04007 (2021)"},{"key":"6_CR36","doi-asserted-by":"crossref","unstructured":"Wang, L., Wang, Y., Wang, L., Zhan, Y., Wang, Y., Lu, H.: Can scale-consistent monocular depth be learned in a self-supervised scale-invariant manner? In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 12727\u201312736 (2021)","DOI":"10.1109\/ICCV48922.2021.01249"},{"key":"6_CR37","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":"6_CR38","doi-asserted-by":"crossref","unstructured":"Yang, J., Alvarez, J.M., Liu, M.: Self-supervised learning of depth inference for multi-view stereo. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 7526\u20137534 (2021)","DOI":"10.1109\/CVPR46437.2021.00744"},{"key":"6_CR39","doi-asserted-by":"crossref","unstructured":"Yang, J., Mao, W., Alvarez, J.M., Liu, M.: Cost volume pyramid based depth inference for multi-view stereo. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4877\u20134886 (2020)","DOI":"10.1109\/CVPR42600.2020.00493"},{"key":"6_CR40","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":"6_CR41","doi-asserted-by":"crossref","unstructured":"Zhao, W., Liu, S., Shu, Y., Liu, Y.J.: Towards better generalization: joint depth-pose learning without posenet. In: 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2020)","DOI":"10.1109\/CVPR42600.2020.00917"},{"key":"6_CR42","doi-asserted-by":"crossref","unstructured":"Zhou, J., Wang, Y., Qin, K., Zeng, W.: Unsupervised high-resolution depth learning from videos with dual networks. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 6872\u20136881 (2019)","DOI":"10.1109\/ICCV.2019.00697"},{"key":"6_CR43","doi-asserted-by":"crossref","unstructured":"Zhou, T., Brown, M., Snavely, N., Lowe, D.G.: Unsupervised learning of depth and ego-motion from video. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2017)","DOI":"10.1109\/CVPR.2017.700"}],"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\/978-3-031-19769-7_6","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,13]],"date-time":"2024-03-13T13:57:01Z","timestamp":1710338221000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-19769-7_6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031197680","9783031197697"],"references-count":43,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-19769-7_6","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":"23 October 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)"}}]}}