{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,2]],"date-time":"2026-01-02T03:05:51Z","timestamp":1767323151789,"version":"3.48.0"},"publisher-location":"Cham","reference-count":31,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032139603","type":"print"},{"value":"9783032139610","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"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\/978-3-032-13961-0_30","type":"book-chapter","created":{"date-parts":[[2026,1,2]],"date-time":"2026-01-02T03:02:25Z","timestamp":1767322945000},"page":"299-309","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["EndoSfM3D: Learning to\u00a03D Reconstruct Any Endoscopic Surgery Scene Using Self-supervised Foundation Model"],"prefix":"10.1007","author":[{"given":"Changhao","family":"Zhang","sequence":"first","affiliation":[]},{"given":"Matthew J.","family":"Clarkson","sequence":"additional","affiliation":[]},{"given":"Mobarak I.","family":"Hoque","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2026,1,2]]},"reference":[{"key":"30_CR1","unstructured":"Al-Obaidi, A., et al.: Effective calibration of an endoscope to an optical tracking system for medical augmented reality. Int. J. Comput. Assist. Radiol. Surg. 12(9), 1619\u20131628 (2017)"},{"key":"30_CR2","unstructured":"Allan, M., et\u00a0al.: Stereo correspondence and reconstruction of endoscopic data challenge. arXiv preprint: arXiv:2101.01133 (2021)"},{"issue":"4","key":"30_CR3","doi-asserted-by":"publisher","first-page":"504","DOI":"10.1364\/JOSAA.414504","volume":"38","author":"P An","year":"2021","unstructured":"An, P., et al.: Two-point calibration method for a zoom camera with an approximate focal-invariant radial distortion model. J. Opt. Soc. Am. A 38(4), 504\u2013514 (2021)","journal-title":"J. Opt. Soc. Am. A"},{"key":"30_CR4","doi-asserted-by":"crossref","unstructured":"Arampatzakis, V., Pavlidis, G., Mitianoudis, N., Papamarkos, N.: Monocular depth estimation: a thorough review. IEEE Trans. Pattern Anal. Mach. Intell. (2023)","DOI":"10.1109\/TPAMI.2023.3330944"},{"key":"30_CR5","doi-asserted-by":"crossref","unstructured":"Bhat, S.F., Alhashim, I., Wonka, P.: LocalBins: improving depth estimation by learning local distributions. In: European Conference on Computer Vision, pp. 480\u2013496. Springer (2022)","DOI":"10.1007\/978-3-031-19769-7_28"},{"key":"30_CR6","unstructured":"Bian, J., et al.: Unsupervised scale-consistent depth and ego-motion learning from monocular video. In: Advances in Neural Information Processing Systems, vol. 32 (2019)"},{"key":"30_CR7","doi-asserted-by":"publisher","first-page":"102956","DOI":"10.1016\/j.media.2023.102956","volume":"90","author":"TL Bobrow","year":"2023","unstructured":"Bobrow, T.L., Golhar, M., Vijayan, R., Akshintala, V.S., Garcia, J.R., Durr, N.J.: Colonoscopy 3D video dataset with paired depth from 2D\u20133D registration. Med. Image Anal. 90, 102956 (2023)","journal-title":"Med. Image Anal."},{"issue":"1","key":"30_CR8","doi-asserted-by":"publisher","first-page":"371","DOI":"10.1109\/TMI.2020.3027442","volume":"40","author":"T Collins","year":"2020","unstructured":"Collins, T., et al.: Augmented reality guided laparoscopic surgery of the uterus. IEEE Trans. Med. Imaging 40(1), 371\u2013380 (2020)","journal-title":"IEEE Trans. Med. Imaging"},{"key":"30_CR9","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":"30_CR10","doi-asserted-by":"crossref","unstructured":"Eppenga, R., et al.: An improved camera model for oblique-viewing laparoscopes: high reprojection accuracy independent of telescope rotation. Phys. Med. Biol. 68(18), 185007 (2023)","DOI":"10.1088\/1361-6560\/acf08f"},{"key":"30_CR11","doi-asserted-by":"crossref","unstructured":"Fang, Z., Chen, X., Chen, Y., Gool, L.V.: Towards good practice for CNN-Based monocular depth estimation. In: Proceedings of the IEEE Winter Conference on Applications of Computer Vision, pp. 1091\u20131100 (2020)","DOI":"10.1109\/WACV45572.2020.9093334"},{"key":"30_CR12","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"},{"key":"30_CR13","doi-asserted-by":"crossref","unstructured":"Gordon, A., Li, H., Jonschkowski, R., Angelova, A.: Depth from videos in the wild: unsupervised monocular depth learning from unknown cameras. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 8977\u20138986 (2019)","DOI":"10.1109\/ICCV.2019.00907"},{"issue":"1","key":"30_CR14","doi-asserted-by":"publisher","first-page":"135","DOI":"10.1109\/TMI.2013.2282997","volume":"33","author":"OG Grasa","year":"2013","unstructured":"Grasa, O.G., Bernal, E., Casado, S., Gil, I., Montiel, J.: Visual slam for handheld monocular endoscope. IEEE Trans. Med. Imaging 33(1), 135\u2013146 (2013)","journal-title":"IEEE Trans. Med. Imaging"},{"key":"30_CR15","unstructured":"Liu, S.Y., et al.: DoRA: weight-decomposed low-rank adaptation. In: Forty-first International Conference on Machine Learning (2024)"},{"key":"30_CR16","unstructured":"Mountney, P., et al.: Endoscopic camera calibration and its application in laparoscopic surgery. In: MICCAI 2011, LNCS. vol.\u00a06891, pp. 473\u2013480 (2011)"},{"key":"30_CR17","unstructured":"Oquab, M., et\u00a0al.: DINOv2: learning robust visual features without supervision. arXiv preprint: arXiv:2304.07193 (2023)"},{"key":"30_CR18","doi-asserted-by":"publisher","first-page":"102058","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."},{"key":"30_CR19","doi-asserted-by":"crossref","unstructured":"Paruchuri, A., et al.: Leveraging near-field lighting for monocular depth estimation from endoscopy videos. In: European Conference on Computer Vision, pp. 473\u2013491. Springer (2024)","DOI":"10.1007\/978-3-031-73411-3_27"},{"key":"30_CR20","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"},{"key":"30_CR21","doi-asserted-by":"publisher","first-page":"83","DOI":"10.1016\/j.compbiomed.2015.09.021","volume":"67","author":"S Rattanalappaiboon","year":"2015","unstructured":"Rattanalappaiboon, S., Bhongmakapat, T., Ritthipravat, P.: Fuzzy zoning for feature matching technique in 3D reconstruction of nasal endoscopic images. Comput. Biol. Med. 67, 83\u201394 (2015)","journal-title":"Comput. Biol. Med."},{"issue":"4","key":"30_CR22","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":"30_CR23","doi-asserted-by":"publisher","first-page":"102338","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":"30_CR24","doi-asserted-by":"publisher","first-page":"103379","DOI":"10.1016\/j.media.2024.103379","volume":"99","author":"PEC Solano","year":"2025","unstructured":"Solano, P.E.C., Bulpitt, A., Subramanian, V., Ali, S.: Multi-task learning with cross-task consistency for improved depth estimation in colonoscopy. Med. Image Anal. 99, 103379 (2025)","journal-title":"Med. Image Anal."},{"key":"30_CR25","doi-asserted-by":"crossref","unstructured":"Spencer, J., Bowden, R., Hadfield, S.: DeFeat-Net: general monocular depth via simultaneous unsupervised representation learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 14402\u201314413 (2020)","DOI":"10.1109\/CVPR42600.2020.01441"},{"key":"30_CR26","doi-asserted-by":"crossref","unstructured":"Sun, L., Bian, J.W., Zhan, H., Yin, W., Reid, I., Shen, C.: SC-DepthV3: robust self-supervised monocular depth estimation for dynamic scenes. IEEE Trans. Pattern Anal. Mach. Intell. (2023)","DOI":"10.1109\/TPAMI.2023.3322549"},{"key":"30_CR27","doi-asserted-by":"crossref","unstructured":"Yang, L., et al.: Depth anything V2. In: Advances in Neural Information Processing Systems, vol. 37, pp. 21875\u201321911 (2024)","DOI":"10.52202\/079017-0688"},{"key":"30_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":"30_CR29","unstructured":"Zeinoddin, M.S., et al.: Endo-FAST3r: endoscopic foundation model adaptation for structure from motion. arXiv preprint: arXiv:2503.07204 (2025)"},{"key":"30_CR30","unstructured":"Zeinoddin, M.S., et\u00a0al.: DARES: depth anything in robotic endoscopic surgery with self-supervised vector-lora of the foundation model. arXiv preprint: arXiv:2408.17433 (2024)"},{"key":"30_CR31","doi-asserted-by":"publisher","first-page":"3449","DOI":"10.1007\/s00464-019-07121-1","volume":"34","author":"P Zhang","year":"2020","unstructured":"Zhang, P., et al.: Real-time navigation for laparoscopic hepatectomy using image fusion of preoperative 3D surgical plan and intraoperative indocyanine green fluorescence imaging. Surg. Endosc. 34, 3449\u20133459 (2020)","journal-title":"Surg. Endosc."}],"container-title":["Lecture Notes in Computer Science","Efficient Medical Artificial Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-13961-0_30","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,2]],"date-time":"2026-01-02T03:02:27Z","timestamp":1767322947000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-13961-0_30"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032139603","9783032139610"],"references-count":31,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-13961-0_30","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]},"assertion":[{"value":"2 January 2026","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":"EMA4MICCAI 2025","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Workshop on Efficient Medical Artificial Intelligence","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":"1","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ema4miccai2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/sites.google.com\/view\/ema4miccai2025","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}