{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,14]],"date-time":"2026-04-14T19:48:24Z","timestamp":1776196104396,"version":"3.50.1"},"publisher-location":"Cham","reference-count":24,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031720888","type":"print"},{"value":"9783031720895","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"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":[[2024]]},"DOI":"10.1007\/978-3-031-72089-5_25","type":"book-chapter","created":{"date-parts":[[2024,10,2]],"date-time":"2024-10-02T16:02:20Z","timestamp":1727884940000},"page":"263-273","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["Enhanced Scale-Aware Depth Estimation for\u00a0Monocular Endoscopic Scenes with\u00a0Geometric Modeling"],"prefix":"10.1007","author":[{"given":"Ruofeng","family":"Wei","sequence":"first","affiliation":[]},{"given":"Bin","family":"Li","sequence":"additional","affiliation":[]},{"given":"Kai","family":"Chen","sequence":"additional","affiliation":[]},{"given":"Yiyao","family":"Ma","sequence":"additional","affiliation":[]},{"given":"Yunhui","family":"Liu","sequence":"additional","affiliation":[]},{"given":"Qi","family":"Dou","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,10,3]]},"reference":[{"key":"25_CR1","unstructured":"Allan, M., Shvets, A., Kurmann, T., Zhang, Z., Duggal, R., Su, Y.H., Rieke, N., Laina, I., Kalavakonda, N., Bodenstedt, S., et\u00a0al.: 2017 robotic instrument segmentation challenge. arXiv preprint arXiv:1902.06426 (2019)"},{"key":"25_CR2","doi-asserted-by":"crossref","unstructured":"Doignon, C., de\u00a0Mathelin, M.: A degenerate conic-based method for a direct fitting and 3-d pose of cylinders with a single perspective view. In: Proceedings 2007 IEEE International Conference on Robotics and Automation. pp. 4220\u20134225 (2007)","DOI":"10.1109\/ROBOT.2007.364128"},{"issue":"10","key":"25_CR3","doi-asserted-by":"publisher","first-page":"16940","DOI":"10.1109\/TITS.2022.3160741","volume":"23","author":"X Dong","year":"2022","unstructured":"Dong, X., Garratt, M.A., Anavatti, S.G., Abbass, H.A.: Towards real-time monocular depth estimation for robotics: A survey. IEEE Transactions on Intelligent Transportation Systems 23(10), 16940\u201316961 (2022)","journal-title":"IEEE Transactions on Intelligent Transportation Systems"},{"key":"25_CR4","unstructured":"Eigen, D., Puhrsch, C., Fergus, R.: Depth map prediction from a single image using a multi-scale deep network. Advances in Neural Information Processing Systems 27 (2014)"},{"key":"25_CR5","doi-asserted-by":"crossref","unstructured":"Godard, C., Mac\u00a0Aodha, 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"},{"issue":"6","key":"25_CR6","doi-asserted-by":"publisher","first-page":"1397","DOI":"10.1109\/TPAMI.2012.213","volume":"35","author":"K He","year":"2012","unstructured":"He, K., Sun, J., Tang, X.: Guided image filtering. IEEE Transactions on Pattern Analysis and Machine Intelligence 35(6), 1397\u20131409 (2012)","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"25_CR7","doi-asserted-by":"crossref","unstructured":"Li, B., Liu, B., Zhu, M., Luo, X., Zhou, F.: Image intrinsic-based unsupervised monocular depth estimation in endoscopy. IEEE Journal of Biomedical and Health Informatics (2024)","DOI":"10.36227\/techrxiv.24345688.v2"},{"key":"25_CR8","unstructured":"Lin, S., Zhi, Y., Yip, M.C.: Semhint-md: Learning from noisy semantic labels for self-supervised monocular depth estimation. arXiv preprint arXiv:2303.18219 (2023)"},{"key":"25_CR9","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2021.102058","volume":"71","author":"KB Ozyoruk","year":"2021","unstructured":"Ozyoruk, K.B., Gokceler, G.I., Bobrow, T.L., Coskun, G., Incetan, K., Almalioglu, Y., Mahmood, F., Curto, E., Perdigoto, L., Oliveira, M., et\u00a0al.: Endoslam dataset and an unsupervised monocular visual odometry and depth estimation approach for endoscopic videos. Medical image analysis 71, 102058 (2021)","journal-title":"Medical image analysis"},{"key":"25_CR10","doi-asserted-by":"crossref","unstructured":"Petrovai, A., Nedevschi, S.: Exploiting pseudo labels in a self-supervised learning framework for improved monocular depth estimation. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition. pp. 1578\u20131588 (2022)","DOI":"10.1109\/CVPR52688.2022.00163"},{"key":"25_CR11","doi-asserted-by":"crossref","unstructured":"Ranftl, R., Bochkovskiy, A., Koltun, V.: Vision transformers for dense prediction. In: Proceedings of the IEEE\/CVF international conference on computer vision. pp. 12179\u201312188 (2021)","DOI":"10.1109\/ICCV48922.2021.01196"},{"issue":"4","key":"25_CR12","doi-asserted-by":"publisher","first-page":"7225","DOI":"10.1109\/LRA.2021.3095528","volume":"6","author":"D Recasens","year":"2021","unstructured":"Recasens, D., Lamarca, J., F\u00e1cil, J.M., Montiel, J., Civera, J.: Endo-depth-and-motion: Reconstruction and tracking in endoscopic videos using depth networks and photometric constraints. IEEE Robotics and Automation Letters 6(4), 7225\u20137232 (2021)","journal-title":"IEEE Robotics and Automation Letters"},{"key":"25_CR13","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2021.102338","volume":"77","author":"S Shao","year":"2022","unstructured":"Shao, S., Pei, Z., Chen, W., Zhu, W., Wu, X., Sun, D., Zhang, B.: Self-supervised monocular depth and ego-motion estimation in endoscopy: Appearance flow to the rescue. Medical image analysis 77, 102338 (2022)","journal-title":"Medical image analysis"},{"key":"25_CR14","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014)"},{"key":"25_CR15","doi-asserted-by":"crossref","unstructured":"Watson, J., Mac\u00a0Aodha, 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"},{"issue":"2","key":"25_CR16","doi-asserted-by":"publisher","first-page":"488","DOI":"10.1109\/TBME.2022.3195027","volume":"70","author":"R Wei","year":"2022","unstructured":"Wei, R., Li, B., Mo, H., Lu, B., Long, Y., Yang, B., Dou, Q., Liu, Y., Sun, D.: Stereo dense scene reconstruction and accurate localization for learning-based navigation of laparoscope in minimally invasive surgery. IEEE Transactions on Biomedical Engineering 70(2), 488\u2013500 (2022)","journal-title":"IEEE Transactions on Biomedical Engineering"},{"key":"25_CR17","doi-asserted-by":"crossref","unstructured":"Wei, R., Li, B., Mo, H., Zhong, F., Long, Y., Dou, Q., Liu, Y.H., Sun, D.: Distilled visual and robot kinematics embeddings for metric depth estimation in monocular scene reconstruction. In: 2022 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS). pp. 8072\u20138077 (2022)","DOI":"10.1109\/IROS47612.2022.9982145"},{"key":"25_CR18","doi-asserted-by":"crossref","unstructured":"Wei, R., Li, B., Zhong, F., Mo, H., Dou, Q., Liu, Y.H., Sun, D.: Absolute monocular depth estimation on robotic visual and kinematics data via self-supervised learning. IEEE Transactions on Automation Science and Engineering (2024)","DOI":"10.1109\/TASE.2024.3409392"},{"key":"25_CR19","doi-asserted-by":"crossref","unstructured":"Xu, J., Li, B., Lu, B., Liu, Y.H., Dou, Q., Heng, P.A.: Surrol: An open-source reinforcement learning centered and dvrk compatible platform for surgical robot learning. In: 2021 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS). pp. 1821\u20131828 (2021)","DOI":"10.1109\/IROS51168.2021.9635867"},{"key":"25_CR20","doi-asserted-by":"crossref","unstructured":"Xue, F., Zhuo, G., Huang, Z., Fu, W., Wu, Z., Ang, M.H.: Toward hierarchical self-supervised monocular absolute depth estimation for autonomous driving applications. In: 2020 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS). pp. 2330\u20132337 (2020)","DOI":"10.1109\/IROS45743.2020.9340802"},{"key":"25_CR21","doi-asserted-by":"crossref","unstructured":"Yang, L., Kang, B., Huang, Z., Xu, X., Feng, J., Zhao, H.: Depth anything: Unleashing the power of large-scale unlabeled data. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 10371\u201310381 (2024)","DOI":"10.1109\/CVPR52733.2024.00987"},{"key":"25_CR22","doi-asserted-by":"crossref","unstructured":"Yang, Z., Pan, J., Dai, J., Sun, Z., Xiao, Y.: Self-supervised lightweight depth estimation in endoscopy combining cnn and transformer. IEEE Transactions on Medical Imaging (2024)","DOI":"10.1109\/TMI.2024.3352390"},{"issue":"6654","key":"25_CR23","doi-asserted-by":"publisher","first-page":"141","DOI":"10.1126\/science.adj3312","volume":"381","author":"M Yip","year":"2023","unstructured":"Yip, M., Salcudean, S., Goldberg, K., Althoefer, K., Menciassi, A., Opfermann, J.D., Krieger, A., Swaminathan, K., Walsh, C.J., Huang, H., et\u00a0al.: Artificial intelligence meets medical robotics. Science 381(6654), 141\u2013146 (2023)","journal-title":"Science"},{"key":"25_CR24","doi-asserted-by":"crossref","unstructured":"Zhang, S., Zhang, J., Tao, D.: Towards scale-aware, robust, and generalizable unsupervised monocular depth estimation by integrating imu motion dynamics. In: European Conference on Computer Vision. pp. 143\u2013160. Springer (2022)","DOI":"10.1007\/978-3-031-19839-7_9"}],"container-title":["Lecture Notes in Computer Science","Medical Image Computing and Computer Assisted Intervention \u2013 MICCAI 2024"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-72089-5_25","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,2]],"date-time":"2024-10-02T16:05:28Z","timestamp":1727885128000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-72089-5_25"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"ISBN":["9783031720888","9783031720895"],"references-count":24,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-72089-5_25","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]},"assertion":[{"value":"3 October 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"The authors have no competing interests to declare that are relevant to the content of this article.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Disclosure of Interests"}},{"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":"Marrakesh","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Morocco","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"7 October 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"11 October 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"miccai2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/conferences.miccai.org\/2024\/en\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}