{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,14]],"date-time":"2026-07-14T14:53:50Z","timestamp":1784040830488,"version":"3.55.0"},"publisher-location":"Cham","reference-count":31,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032051400","type":"print"},{"value":"9783032051417","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,9,20]],"date-time":"2025-09-20T00:00:00Z","timestamp":1758326400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,9,20]],"date-time":"2025-09-20T00:00:00Z","timestamp":1758326400000},"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\/978-3-032-05141-7_12","type":"book-chapter","created":{"date-parts":[[2025,9,19]],"date-time":"2025-09-19T08:15:48Z","timestamp":1758269748000},"page":"117-126","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Endo-FASt3r: Endoscopic Foundation Model Adaptation for\u00a0Structure from\u00a0Motion"],"prefix":"10.1007","author":[{"given":"Mona","family":"Sheikh Zeinoddin","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mobarak I.","family":"Hoque","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zafer","family":"Tandogdu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Greg L.","family":"Shaw","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Matthew J.","family":"Clarkson","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Evangelos B.","family":"Mazomenos","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Danail","family":"Stoyanov","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,9,20]]},"reference":[{"issue":"1","key":"12_CR1","doi-asserted-by":"publisher","first-page":"184","DOI":"10.1038\/s41746-022-00733-3","volume":"5","author":"S Ali","year":"2022","unstructured":"Ali, S.: Where do we stand in ai for endoscopic image analysis? deciphering gaps and future directions. NPJ Digit. Med. 5(1), 184 (2022)","journal-title":"NPJ Digit. Med."},{"key":"12_CR2","unstructured":"Allan, M., et\u00a0al.: Stereo correspondence and reconstruction of endoscopic data challenge. arXiv (2021)"},{"key":"12_CR3","unstructured":"Bian, J., et al.: Unsupervised scale-consistent depth and ego-motion learning from monocular video. Neural Inf. Process. Syst. 32 (2019)"},{"key":"12_CR4","doi-asserted-by":"publisher","first-page":"135","DOI":"10.1016\/j.cmpb.2018.02.006","volume":"158","author":"L Chen","year":"2018","unstructured":"Chen, L., Tang, W., John, N.W., Wan, T.R., Zhang, J.J.: Slam-based dense surface reconstruction in monocular minimally invasive surgery and its application to augmented reality. Comput. Methods Programs Biomed. 158, 135\u2013146 (2018)","journal-title":"Comput. Methods Programs Biomed."},{"key":"12_CR5","doi-asserted-by":"crossref","unstructured":"Cui, B., Islam, M., Bai, L., Ren, H.: Surgical-dino: adapter learning of foundation models for depth estimation in endoscopic surgery. Int. J. Comput. Assist. Radiol. Surg., 1\u20138 (2024)","DOI":"10.1007\/s11548-024-03083-5"},{"key":"12_CR6","doi-asserted-by":"publisher","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: MICCAI, pp. 208\u2013218. Springer (2024). https:\/\/doi.org\/10.1007\/978-3-031-72089-5_20","DOI":"10.1007\/978-3-031-72089-5_20"},{"key":"12_CR7","doi-asserted-by":"crossref","unstructured":"Dong, S., et al.: Reloc3r: Large-scale training of relative camera pose regression for generalizable, fast, and accurate visual localization. arXiv (2024)","DOI":"10.1109\/CVPR52734.2025.01560"},{"key":"12_CR8","doi-asserted-by":"crossref","unstructured":"Godard, C., Mac\u00a0Aodha, O., Firman, M., Brostow, G.J.: Digging into self-supervised monocular depth estimation. In: CVPR, pp. 3828\u20133838 (2019)","DOI":"10.1109\/ICCV.2019.00393"},{"key":"12_CR9","doi-asserted-by":"crossref","unstructured":"Hayoz, M., et al.: Learning how to robustly estimate camera pose in endoscopic videos. Inter. J. Comput. Assisted Radiol. Surgery 18(7), 1185\u20131192 (2023)","DOI":"10.1007\/s11548-023-02919-w"},{"key":"12_CR10","unstructured":"Hu, E.J., et al.: Lora: Low-rank adaptation of large language models. arXiv (2021)"},{"key":"12_CR11","unstructured":"Jiang, T., et\u00a0al.: Mora: High-rank updating for parameter-efficient fine-tuning. arXiv (2024)"},{"key":"12_CR12","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 J. Biomed. Health Inform (2024)","DOI":"10.36227\/techrxiv.24345688.v2"},{"key":"12_CR13","unstructured":"Liu, S.Y., et al.: Dora: Weight-decomposed low-rank adaptation. arXiv (2024)"},{"issue":"5","key":"12_CR14","doi-asserted-by":"publisher","first-page":"1147","DOI":"10.1109\/TRO.2015.2463671","volume":"31","author":"R Mur-Artal","year":"2015","unstructured":"Mur-Artal, R., Montiel, J.M.M., Tardos, J.D.: Orb-slam: a versatile and accurate monocular slam system. IEEE Trans. Robot. 31(5), 1147\u20131163 (2015)","journal-title":"IEEE Trans. Robot."},{"key":"12_CR15","doi-asserted-by":"crossref","unstructured":"Murray, R.M., Li, Z., Sastry, S.S.: A mathematical introduction to robotic manipulation. CRC press (2017)","DOI":"10.1201\/9781315136370"},{"key":"12_CR16","unstructured":"Oquab, M., et\u00a0al.: Dinov2: Learning robust visual features without supervision. arXiv (2023)"},{"key":"12_CR17","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2021.102058","volume":"71","author":"KB Ozyoruk","year":"2021","unstructured":"Ozyoruk, K.B., et al.: Endoslam dataset and an unsupervised monocular visual odometry and depth estimation approach for endoscopic videos. Med. Image Anal. 71, 102058 (2021)","journal-title":"Med. Image Anal."},{"issue":"1","key":"12_CR18","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/TMRB.2019.2957061","volume":"2","author":"L Qian","year":"2019","unstructured":"Qian, L., Wu, J.Y., DiMaio, S.P., Navab, N., Kazanzides, P.: A review of augmented reality in robotic-assisted surgery. IEEE Trans. Med. Robot. Bionics 2(1), 1\u201316 (2019)","journal-title":"IEEE Trans. Med. Robot. Bionics"},{"issue":"4","key":"12_CR19","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 Robot. Autom. Lett. 6(4), 7225\u20137232 (2021)","journal-title":"IEEE Robot. Autom. Lett."},{"key":"12_CR20","unstructured":"Salimans, T., Kingma, D.P.: Weight normalization: A simple reparameterization to accelerate training of deep neural networks. Neural Inf. Process. Syst. 29 (2016)"},{"key":"12_CR21","doi-asserted-by":"crossref","unstructured":"Schmidt, A., Mohareri, O., DiMaio, S., Yip, M.C., Salcudean, S.E.: Tracking and mapping in medical computer vision: a review. Med. Image Anal., 103131 (2024)","DOI":"10.1016\/j.media.2024.103131"},{"key":"12_CR22","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_CR23","doi-asserted-by":"crossref","unstructured":"Spencer, J., Bowden, R., Hadfield, S.: Defeat-net: general monocular depth via simultaneous unsupervised representation learning. In: CVPR, pp. 14402\u201314413 (2020)","DOI":"10.1109\/CVPR42600.2020.01441"},{"key":"12_CR24","doi-asserted-by":"crossref","unstructured":"Wang, C., Buenaposada, J.M., Zhu, R., Lucey, S.: Learning depth from monocular videos using direct methods. In: CVPR, pp. 2022\u20132030 (2018)","DOI":"10.1109\/CVPR.2018.00216"},{"key":"12_CR25","unstructured":"Wang, Z., Simoncelli, E.P., Bovik, A.C.: Multiscale structural similarity for image quality assessment. In: Asilomar Conf. Signals Syst. Comput, vol.\u00a02, pp. 1398\u20131402. IEEE (2003)"},{"key":"12_CR26","unstructured":"Yang, H., et al.: Depth any video with scalable synthetic data. arXiv (2024)"},{"key":"12_CR27","unstructured":"Yang, L., et al.: Depth anything v2. arXiv (2024)"},{"key":"12_CR28","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 Trans. Med. Imaging (2024)","DOI":"10.1109\/TMI.2024.3352390"},{"key":"12_CR29","doi-asserted-by":"publisher","unstructured":"Zeinoddin, M.S., et\u00a0al.: Dares: Depth anything in robotic endoscopic surgery with self-supervised vector-lora of the foundation model. In: ECCV. Springer (2024). https:\/\/doi.org\/10.1007\/978-3-031-91979-4_1","DOI":"10.1007\/978-3-031-91979-4_1"},{"issue":"1","key":"12_CR30","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s12213-024-00181-0","volume":"21","author":"J Zhong","year":"2025","unstructured":"Zhong, J., Ren, H., Chen, Q., Zhang, H.: A review of deep learning-based localization, mapping and 3d reconstruction for endoscopy. J. Micro Bio Robot. 21(1), 1\u201325 (2025)","journal-title":"J. Micro Bio Robot."},{"key":"12_CR31","doi-asserted-by":"crossref","unstructured":"Zhou, T., Brown, M., Snavely, N., Lowe, D.G.: Unsupervised learning of depth and ego-motion from video. In: CVPR, 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 2025"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-05141-7_12","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,19]],"date-time":"2025-09-19T08:15:57Z","timestamp":1758269757000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-05141-7_12"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,20]]},"ISBN":["9783032051400","9783032051417"],"references-count":31,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-05141-7_12","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,9,20]]},"assertion":[{"value":"20 September 2025","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":"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":"27 September 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"28","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"miccai2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/conferences.miccai.org\/2025\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}