{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,18]],"date-time":"2026-07-18T17:56:14Z","timestamp":1784397374770,"version":"3.55.0"},"publisher-location":"Cham","reference-count":30,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031439957","type":"print"},{"value":"9783031439964","type":"electronic"}],"license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023]]},"DOI":"10.1007\/978-3-031-43996-4_41","type":"book-chapter","created":{"date-parts":[[2023,9,30]],"date-time":"2023-09-30T23:07:48Z","timestamp":1696115268000},"page":"429-439","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":8,"title":["Multi-view Guidance for\u00a0Self-supervised Monocular Depth Estimation on\u00a0Laparoscopic Images via\u00a0Spatio-Temporal Correspondence"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4486-7207","authenticated-orcid":false,"given":"Wenda","family":"Li","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuichiro","family":"Hayashi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7714-422X","authenticated-orcid":false,"given":"Masahiro","family":"Oda","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1648-1999","authenticated-orcid":false,"given":"Takayuki","family":"Kitasaka","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2047-3919","authenticated-orcid":false,"given":"Kazunari","family":"Misawa","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0100-4797","authenticated-orcid":false,"given":"Kensaku","family":"Mori","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2023,10,1]]},"reference":[{"key":"41_CR1","unstructured":"Allan, M., et al.: Stereo correspondence and reconstruction of endoscopic data challenge. arXiv preprint arXiv:2101.01133 (2021)"},{"key":"41_CR2","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 27 (2014)"},{"key":"41_CR3","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":"41_CR4","doi-asserted-by":"crossref","unstructured":"Guizilini, V., Hou, R., Li, J., Ambrus, R., Gaidon, A.: Semantically-guided representation learning for self-supervised monocular depth. arXiv preprint arXiv:2002.12319 (2020)","DOI":"10.1109\/CVPR42600.2020.00256"},{"key":"41_CR5","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 Recognitionm, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"41_CR6","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"227","DOI":"10.1007\/978-3-030-87202-1_22","volume-title":"Medical Image Computing and Computer Assisted Intervention \u2013 MICCAI 2021","author":"B Huang","year":"2021","unstructured":"Huang, B., et al.: Self-supervised generative adversarial network for depth estimation in\u00a0laparoscopic images. In: de Bruijne, M., Cattin, P.C., Cotin, S., Padoy, N., Speidel, S., Zheng, Y., Essert, C. (eds.) MICCAI 2021. LNCS, vol. 12904, pp. 227\u2013237. Springer, Cham (2021). https:\/\/doi.org\/10.1007\/978-3-030-87202-1_22"},{"key":"41_CR7","doi-asserted-by":"crossref","unstructured":"Hwang, M., et al.: Applying depth-sensing to automated surgical manipulation with a da Vinci robot. In: 2020 International Symposium on Medical Robotics (ISMR), pp. 22\u201329. IEEE (2020)","DOI":"10.1109\/ISMR48331.2020.9312948"},{"key":"41_CR8","unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)"},{"key":"41_CR9","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":"41_CR10","doi-asserted-by":"crossref","unstructured":"Li, W., Hayashi, Y., Oda, M., Kitasaka, T., Misawa, K., Kensaku, M.: Attention guided self-supervised monocular depth estimation based on joint depth-pose loss for laparoscopic images. Comput. Assist. Radiol. Surg. (2022)","DOI":"10.1117\/12.2582348"},{"key":"41_CR11","unstructured":"Li, W., Hayashi, Y., Oda, M., Kitasaka, T., Misawa, K., Mori, K.: Spatially variant biases considered self-supervised depth estimation based on laparoscopic videos. Comput. Methods Biomech. Biomed. Eng.: Imaging Vis., 1\u20139 (2021)"},{"key":"41_CR12","doi-asserted-by":"publisher","unstructured":"Li, W., Hayashi, Y., Oda, M., Kitasaka, T., Misawa, K., Mori, K.: Geometric constraints for self-supervised monocular depth estimation on laparoscopic images with dual-task consistency. In: Medical Image Computing and Computer Assisted Intervention-MICCAI 2022: 25th International Conference, Singapore, September 18\u201322, 2022, Proceedings, LNCS, Part IV, pp. 467\u2013477. Springer (2022). https:\/\/doi.org\/10.1007\/978-3-031-16440-8_45","DOI":"10.1007\/978-3-031-16440-8_45"},{"key":"41_CR13","doi-asserted-by":"crossref","unstructured":"Lyu, X., Liu, L., Wang, M., Kong, X., Liu, L., Liu, Y., Chen, X., Yuan, Y.: HR-Depth: high resolution self-supervised monocular depth estimation. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 35, pp. 2294\u20132301 (2021)","DOI":"10.1609\/aaai.v35i3.16329"},{"key":"41_CR14","doi-asserted-by":"publisher","first-page":"14","DOI":"10.1016\/j.neucom.2020.12.089","volume":"438","author":"Y Ming","year":"2021","unstructured":"Ming, Y., Meng, X., Fan, C., Yu, H.: Deep learning for monocular depth estimation: a review. Neurocomputing 438, 14\u201333 (2021)","journal-title":"Neurocomputing"},{"key":"41_CR15","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"120","DOI":"10.1007\/978-3-030-58601-0_8","volume-title":"Computer Vision \u2013 ECCV 2020","author":"J Park","year":"2020","unstructured":"Park, J., Joo, K., Hu, Z., Liu, C.-K., So Kweon, I.: Non-local spatial propagation network for depth completion. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12358, pp. 120\u2013136. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58601-0_8"},{"key":"41_CR16","unstructured":"Paszke, A., et al.: Automatic differentiation in PyTorch. In: NIPS 2017 Workshop on Autodiff (2017)"},{"key":"41_CR17","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":"41_CR18","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"74","DOI":"10.1007\/978-3-030-32254-0_9","volume-title":"Medical Image Computing and Computer Assisted Intervention \u2013 MICCAI 2019","author":"L Qian","year":"2019","unstructured":"Qian, L., Zhang, X., Deguet, A., Kazanzides, P.: ARAMIS: augmented reality assistance for minimally invasive surgery using a head-mounted display. In: Shen, D., et al. (eds.) MICCAI 2019. LNCS, vol. 11768, pp. 74\u201382. Springer, Cham (2019). https:\/\/doi.org\/10.1007\/978-3-030-32254-0_9"},{"issue":"3","key":"41_CR19","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":"6","key":"41_CR20","doi-asserted-by":"publisher","first-page":"311","DOI":"10.3109\/13645706.2010.541921","volume":"20","author":"P S\u00e1nchez-Gonz\u00e1lez","year":"2011","unstructured":"S\u00e1nchez-Gonz\u00e1lez, P., et al.: Laparoscopic video analysis for training and image-guided surgery. Minim. Invasive Therapy Allied Technol. 20(6), 311\u2013320 (2011)","journal-title":"Minim. Invasive Therapy Allied Technol."},{"key":"41_CR21","doi-asserted-by":"crossref","unstructured":"Tosi, F., Aleotti, F., Poggi, M., Mattoccia, S.: Learning monocular depth estimation infusing traditional stereo knowledge. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9799\u20139809 (2019)","DOI":"10.1109\/CVPR.2019.01003"},{"issue":"1","key":"41_CR22","first-page":"87","volume":"42","author":"R Vecchio","year":"2000","unstructured":"Vecchio, R., MacFayden, B., Palazzo, F.: History of laparoscopic surgery. Panminerva Med. 42(1), 87\u201390 (2000)","journal-title":"Panminerva Med."},{"key":"41_CR23","doi-asserted-by":"crossref","unstructured":"Wang, F., Galliani, S., Vogel, C., Speciale, P., Pollefeys, M.: Patchmatchnet: learned multi-view patchmatch stereo. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 14194\u201314203 (2021)","DOI":"10.1109\/CVPR46437.2021.01397"},{"issue":"4","key":"41_CR24","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":"41_CR25","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":"41_CR26","doi-asserted-by":"crossref","unstructured":"Yao, Y., Luo, Z., Li, S., Fang, T., Quan, L.: MVSNet: depth inference for unstructured multi-view stereo. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 767\u2013783 (2018)","DOI":"10.1007\/978-3-030-01237-3_47"},{"key":"41_CR27","doi-asserted-by":"crossref","unstructured":"Ye, M., Johns, E., Handa, A., Zhang, L., Pratt, P., Yang, G.Z.: Self-supervised siamese learning on stereo image pairs for depth estimation in robotic surgery. arXiv preprint arXiv:1705.08260 (2017)","DOI":"10.31256\/HSMR2017.14"},{"issue":"12","key":"41_CR28","doi-asserted-by":"publisher","first-page":"5392","DOI":"10.1109\/TNNLS.2020.3044181","volume":"32","author":"C Zhao","year":"2020","unstructured":"Zhao, C., Yen, G.G., Sun, Q., Zhang, C., Tang, Y.: Masked GAN for unsupervised depth and pose prediction with scale consistency. IEEE Trans. Neural Netw. Learn. Syst. 32(12), 5392\u20135403 (2020)","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"41_CR29","doi-asserted-by":"crossref","unstructured":"Zhao, C., et al.: MonoViT: self-supervised monocular depth estimation with a vision transformer. arXiv preprint arXiv:2208.03543 (2022)","DOI":"10.1109\/3DV57658.2022.00077"},{"key":"41_CR30","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"}],"container-title":["Lecture Notes in Computer Science","Medical Image Computing and Computer Assisted Intervention \u2013 MICCAI 2023"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-43996-4_41","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,7,4]],"date-time":"2024-07-04T16:08:30Z","timestamp":1720109310000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-43996-4_41"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031439957","9783031439964"],"references-count":30,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-43996-4_41","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]},"assertion":[{"value":"1 October 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"MICCAI","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Medical Image Computing and Computer-Assisted Intervention","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Vancouver, BC","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Canada","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2023","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 October 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12 October 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"miccai2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/conferences.miccai.org\/2023\/en\/","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":"2250","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":"730","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":"32% - 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":"5","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)"}}]}}