{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T05:10:21Z","timestamp":1760159421071,"version":"build-2065373602"},"publisher-location":"Cham","reference-count":26,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032080080","type":"print"},{"value":"9783032080097","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,10,12]],"date-time":"2025-10-12T00:00:00Z","timestamp":1760227200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,10,12]],"date-time":"2025-10-12T00:00:00Z","timestamp":1760227200000},"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":[[2026]]},"DOI":"10.1007\/978-3-032-08009-7_12","type":"book-chapter","created":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T04:37:14Z","timestamp":1760157434000},"page":"115-124","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Zero-Shot Monocular Metric Depth for Endoscopic Images"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4696-465X","authenticated-orcid":false,"given":"Nicolas","family":"Toussaint","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4614-5742","authenticated-orcid":false,"given":"Emanuele","family":"Colleoni","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2330-0973","authenticated-orcid":false,"given":"Ricardo","family":"Sanchez-Matilla","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Joshua","family":"Sutcliffe","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Vanessa","family":"Thompson","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3672-2414","authenticated-orcid":false,"given":"Muhammad","family":"Asad","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6573-322X","authenticated-orcid":false,"given":"Imanol","family":"Luengo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0980-3227","authenticated-orcid":false,"given":"Danail","family":"Stoyanov","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,10,12]]},"reference":[{"key":"12_CR1","unstructured":"Allan, M., et\u00a0al.: Stereo correspondence and reconstruction of endoscopic data challenge. arXiv preprint arXiv:2101.01133 (2021)"},{"key":"12_CR2","unstructured":"Birkl, R., Wofk, D., M\u00fcller, M.: Midas v3. 1\u2013a model zoo for robust monocular relative depth estimation. arXiv preprint arXiv:2307.14460 (2023)"},{"key":"12_CR3","unstructured":"Bochkovskii, A., et al.: Depth Pro: sharp monocular metric depth in less than a second. arXiv preprint arXiv:2410.02073 (2024)"},{"key":"12_CR4","doi-asserted-by":"crossref","unstructured":"Budd, C., Vercauteren, T.: Transferring relative monocular depth to surgical vision with temporal consistency. In: International Conference on Medical Image Computing and Computer-Assisted Intervention, pp. 692\u2013702. Springer (2024)","DOI":"10.1007\/978-3-031-72089-5_65"},{"issue":"2","key":"12_CR5","doi-asserted-by":"publisher","first-page":"125","DOI":"10.3390\/info11020125","volume":"11","author":"A Buslaev","year":"2020","unstructured":"Buslaev, A., Iglovikov, V.I., Khvedchenya, E., Parinov, A., Druzhinin, M., Kalinin, A.A.: Albumentations: fast and flexible image augmentations. Information 11(2), 125 (2020)","journal-title":"Information"},{"key":"12_CR6","doi-asserted-by":"crossref","unstructured":"Cui, B., Islam, M., Bai, L., Wang, A., Ren, H.: EndoDAC: efficient adapting foundation model for self-supervised depth estimation from any endoscopic camera. In: International Conference on Medical Image Computing and Computer-Assisted Intervention, pp. 208\u2013218. Springer (2024)","DOI":"10.1007\/978-3-031-72089-5_20"},{"key":"12_CR7","unstructured":"Eigen, D., Puhrsch, C., Fergus, R.: Depth map prediction from a single image using a multi-scale deep network. Adv. Neural Info. Process. Syst. 27 (2014)"},{"key":"12_CR8","unstructured":"Han, J.J., Acar, A., Henry, C., Wu, J.Y.: Depth anything in medical images: a comparative study. arXiv preprint arXiv:2401.16600 (2024)"},{"issue":"7","key":"12_CR9","doi-asserted-by":"publisher","first-page":"1185","DOI":"10.1007\/s11548-023-02919-w","volume":"18","author":"M Hayoz","year":"2023","unstructured":"Hayoz, M., et al.: Learning how to robustly estimate camera pose in endoscopic videos. Int. J. Comput. Assist. Radiol. Surg. 18(7), 1185\u20131192 (2023)","journal-title":"Int. J. Comput. Assist. Radiol. Surg."},{"key":"12_CR10","unstructured":"Hong, W.Y., Kao, C.L., Kuo, Y.H., Wang, J.R., Chang, W.L., Shih, C.S.: CholecSeg8k: a semantic segmentation dataset for laparoscopic cholecystectomy based on cholec80. arXiv preprint arXiv:2012.12453 (2020)"},{"key":"12_CR11","unstructured":"Kingma, D.P.: Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)"},{"issue":"6","key":"12_CR12","doi-asserted-by":"publisher","first-page":"780","DOI":"10.1038\/s41551-023-01010-8","volume":"7","author":"D Kiyasseh","year":"2023","unstructured":"Kiyasseh, D., et al.: A vision transformer for decoding surgeon activity from surgical videos. Nature Biomed. Eng. 7(6), 780\u2013796 (2023)","journal-title":"Nature Biomed. Eng."},{"issue":"1","key":"12_CR13","doi-asserted-by":"publisher","first-page":"99","DOI":"10.1007\/s11701-024-01838-5","volume":"18","author":"JCY Ngu","year":"2024","unstructured":"Ngu, J.C.Y., Lin, C.C.W., Sia, C.J.Y., Teo, N.Z.: A narrative review of the Medtronic Hugo RAS and technical comparison with the intuitive da Vinci robotic surgical system. J. Robot. Surg. 18(1), 99 (2024)","journal-title":"J. Robot. Surg."},{"key":"12_CR14","unstructured":"Oquab, M., et\u00a0al.: DINOv2: learning robust visual features without supervision. arXiv preprint arXiv:2304.07193 (2023)"},{"key":"12_CR15","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":"3","key":"12_CR16","doi-asserted-by":"publisher","first-page":"1623","DOI":"10.1109\/TPAMI.2020.3019967","volume":"44","author":"R Ranftl","year":"2020","unstructured":"Ranftl, R., Lasinger, K., Hafner, D., Schindler, K., Koltun, V.: Towards robust monocular depth estimation: mixing datasets for zero-shot cross-dataset transfer. IEEE Trans. Pattern Anal. Mach. Intell. 44(3), 1623\u20131637 (2020)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"issue":"4","key":"12_CR17","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.M., Civera, J.: Endo-depth-and-motion: reconstruction and tracking in endoscopic videos using depth networks and photometric constraints. IEEE Robot. Autom. Lett. 6(4), 7225\u20137232 (2021)","journal-title":"IEEE Robot. Autom. Lett."},{"key":"12_CR18","doi-asserted-by":"crossref","unstructured":"Rivoir, D., et al.: Long-term temporally consistent unpaired video translation from simulated surgical 3D data. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 3343\u20133353 (2021)","DOI":"10.1109\/ICCV48922.2021.00333"},{"key":"12_CR19","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2021.102338","volume":"77","author":"S Shao","year":"2022","unstructured":"Shao, S., et al.: Self-supervised monocular depth and ego-motion estimation in endoscopy: Appearance flow to the rescue. Med. Image Anal. 77, 102338 (2022)","journal-title":"Med. Image Anal."},{"key":"12_CR20","doi-asserted-by":"crossref","unstructured":"Tomasi, C., Manduchi, R.: Bilateral filtering for gray and color images. In: Sixth International Conference on Computer Vision (IEEE Cat. No. 98CH36271), pp. 839\u2013846. IEEE (1998)","DOI":"10.1109\/ICCV.1998.710815"},{"key":"12_CR21","doi-asserted-by":"crossref","unstructured":"Walkner, H., Krames, L., Nahm, W.: Synthetic data in supervised monocular depth estimation of laparoscopic liver images. In: Current Directions in Biomedical Engineering, vol.\u00a010, pp. 661\u2013664. De Gruyter (2024)","DOI":"10.1515\/cdbme-2024-2162"},{"key":"12_CR22","doi-asserted-by":"crossref","unstructured":"Wang, Y., Long, Y., Fan, S.H., Dou, Q.: Neural rendering for stereo 3D reconstruction of deformable tissues in robotic surgery. In: International Conference on Medical Image Computing and Computer-assisted Intervention, pp. 431\u2013441. Springer (2022)","DOI":"10.1007\/978-3-031-16449-1_41"},{"key":"12_CR23","doi-asserted-by":"crossref","unstructured":"Xu, H., et al.: Unifying flow, stereo and depth estimation. IEEE Trans. Pattern Anal. Mach. Intell. 45(11) (2023)","DOI":"10.1109\/TPAMI.2023.3298645"},{"key":"12_CR24","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":"12_CR25","unstructured":"Yang, L., et al.: Depth anything V2. arXiv preprint arXiv:2406.09414 (2024)"},{"key":"12_CR26","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)"}],"container-title":["Lecture Notes in Computer Science","Data Engineering in Medical Imaging"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-08009-7_12","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T04:37:21Z","timestamp":1760157441000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-08009-7_12"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,12]]},"ISBN":["9783032080080","9783032080097"],"references-count":26,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-08009-7_12","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,10,12]]},"assertion":[{"value":"12 October 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"DEMI","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"MICCAI Workshop on Data Engineering in Medical Imaging","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Daejeon","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Korea (Republic of)","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23 September 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23 September 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"3","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"demi2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}