{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,21]],"date-time":"2026-05-21T16:40:40Z","timestamp":1779381640854,"version":"3.53.1"},"publisher-location":"Cham","reference-count":39,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032051134","type":"print"},{"value":"9783032051141","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,9,21]],"date-time":"2025-09-21T00:00:00Z","timestamp":1758412800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,9,21]],"date-time":"2025-09-21T00:00:00Z","timestamp":1758412800000},"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\/978-3-032-05114-1_17","type":"book-chapter","created":{"date-parts":[[2025,9,20]],"date-time":"2025-09-20T14:10:24Z","timestamp":1758377424000},"page":"170-180","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Endo3R: Unified Online Reconstruction from\u00a0Dynamic Monocular Endoscopic Video"],"prefix":"10.1007","author":[{"given":"Jiaxin","family":"Guo","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wenzhen","family":"Dong","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tianyu","family":"Huang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hao","family":"Ding","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ziyi","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Haomin","family":"Kuang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qi","family":"Dou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yun-Hui","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,9,21]]},"reference":[{"key":"17_CR1","unstructured":"A. Dosovitskiy et al.: An image is worth 16x16 words: Transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)"},{"issue":"1","key":"17_CR2","doi-asserted-by":"publisher","first-page":"86","DOI":"10.1109\/TMI.2016.2593957","volume":"36","author":"A Twinanda","year":"2016","unstructured":"Twinanda, A., et al.: Endonet: a deep architecture for recognition tasks on laparoscopic videos. IEEE Trans. Med. Imaging 36(1), 86\u201397 (2016)","journal-title":"IEEE Trans. Med. Imaging"},{"key":"17_CR3","doi-asserted-by":"crossref","unstructured":"B. Cui et al.: Endodac: Efficient adapting foundation model for self-supervised depth estimation from any endoscopic camera. In: MICCAI. pp. 208\u2013218. Springer (2024)","DOI":"10.1007\/978-3-031-72089-5_20"},{"issue":"1","key":"17_CR4","doi-asserted-by":"publisher","first-page":"99","DOI":"10.1145\/3503250","volume":"65","author":"B Mildenhall","year":"2021","unstructured":"Mildenhall, B., et al.: Nerf: Representing scenes as neural radiance fields for view synthesis. Commun. ACM 65(1), 99\u2013106 (2021)","journal-title":"Commun. ACM"},{"key":"17_CR5","doi-asserted-by":"crossref","unstructured":"C. Budd et al.: Transferring relative monocular depth to surgical vision with temporal consistency. In: MICCAI. pp. 692\u2013702. Springer (2024)","DOI":"10.1007\/978-3-031-72089-5_65"},{"issue":"6","key":"17_CR6","doi-asserted-by":"publisher","first-page":"1874","DOI":"10.1109\/TRO.2021.3075644","volume":"37","author":"C Campos","year":"2021","unstructured":"Campos, C., et al.: Orb-slam3: An accurate open-source library for visual, visual-inertial, and multimap slam. IEEE Trans. Rob. 37(6), 1874\u20131890 (2021)","journal-title":"IEEE Trans. Rob."},{"key":"17_CR7","doi-asserted-by":"crossref","unstructured":"C. Godard et al.: Digging into self-supervised monocular depth estimation. In: ICCV. pp. 3828\u20133838 (2019)","DOI":"10.1109\/ICCV.2019.00393"},{"issue":"4","key":"17_CR8","first-page":"7225","volume":"6","author":"D Recasens","year":"2021","unstructured":"Recasens, D., et al.: Endo-depth-and-motion: Reconstruction and tracking in endoscopic videos using depth networks and photometric constraints. IEEE RA-L 6(4), 7225\u20137232 (2021)","journal-title":"IEEE RA-L"},{"key":"17_CR9","doi-asserted-by":"crossref","unstructured":"E. Arnold et al.: Map-free visual relocalization: Metric pose relative to a single image. In: ECCV. pp. 690\u2013708. Springer (2022)","DOI":"10.1007\/978-3-031-19769-7_40"},{"key":"17_CR10","unstructured":"H. Wang et al.: 3d reconstruction with spatial memory. arXiv preprint arXiv:2408.16061 (2024)"},{"key":"17_CR11","unstructured":"H. Yang et al.: Depth any video with scalable synthetic data. arXiv preprint arXiv:2410.10815 (2024)"},{"key":"17_CR12","doi-asserted-by":"crossref","unstructured":"J. Guo et al.: A visual navigation perspective for category-level object pose estimation. In: ECCV. pp. 123\u2013141. Springer (2022)","DOI":"10.1007\/978-3-031-20068-7_8"},{"key":"17_CR13","doi-asserted-by":"crossref","unstructured":"J. Guo et al.: Free-surgs: Sfm-free 3d gaussian splatting for surgical scene reconstruction. In: MICCAI. pp. 350\u2013360. Springer (2024)","DOI":"10.1007\/978-3-031-72104-5_34"},{"key":"17_CR14","doi-asserted-by":"crossref","unstructured":"J. Guo et al.: Uc-nerf: Uncertainty-aware conditional neural radiance fields from endoscopic sparse views. IEEE Transactions on Medical Imaging (2024)","DOI":"10.1109\/TMI.2024.3496558"},{"key":"17_CR15","doi-asserted-by":"crossref","unstructured":"J. Schonberger et al.: Structure-from-motion revisited. In: ICCV. pp. 4104\u20134113 (2016)","DOI":"10.1109\/CVPR.2016.445"},{"key":"17_CR16","unstructured":"J. Zhang et al.: Monst3r: A simple approach for estimating geometry in the presence of motion. arXiv preprint arXiv:2410.03825 (2024)"},{"key":"17_CR17","doi-asserted-by":"crossref","unstructured":"Ozyoruk, K., et al.: Endoslam dataset and an unsupervised monocular visual odometry and depth estimation approach for endoscopic videos. Med. Image Anal. 71, 102058 (2021)","DOI":"10.1016\/j.media.2021.102058"},{"key":"17_CR18","first-page":"21875","volume":"37","author":"L Yang","year":"2025","unstructured":"Yang, L., et al.: Depth anything v2. NeurIPS 37, 21875\u201321911 (2025)","journal-title":"NeurIPS"},{"key":"17_CR19","unstructured":"M. Allan et al.: 2017 robotic instrument segmentation challenge. arXiv preprint arXiv:1902.06426 (2019)"},{"key":"17_CR20","unstructured":"M. Allan et al.: 2018 robotic scene segmentation challenge. arXiv preprint arXiv:2001.11190 (2020)"},{"key":"17_CR21","unstructured":"M. Allan et al.: Stereo correspondence and reconstruction of endoscopic data challenge. arXiv:2101.01133 (2021)"},{"issue":"7","key":"17_CR22","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."},{"issue":"1","key":"17_CR23","doi-asserted-by":"publisher","first-page":"671","DOI":"10.1038\/s41597-023-02564-7","volume":"10","author":"P Azagra","year":"2023","unstructured":"Azagra, P., et al.: Endomapper dataset of complete calibrated endoscopy procedures. Scientific Data 10(1), 671 (2023)","journal-title":"Scientific Data"},{"key":"17_CR24","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."},{"issue":"3","key":"17_CR25","doi-asserted-by":"publisher","first-page":"1623","DOI":"10.1109\/TPAMI.2020.3019967","volume":"44","author":"R Ranftl","year":"2020","unstructured":"Ranftl, R., et al.: 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."},{"key":"17_CR26","doi-asserted-by":"crossref","unstructured":"R. Ranftl et al.: Vision transformers for dense prediction. In: ICCV. pp. 12179\u201312188 (2021)","DOI":"10.1109\/ICCV48922.2021.01196"},{"key":"17_CR27","doi-asserted-by":"crossref","unstructured":"R. Wei et al.: Enhanced scale-aware depth estimation for monocular endoscopic scenes with geometric modeling. In: MICCAI. pp. 263\u2013273. Springer (2024)","DOI":"10.1007\/978-3-031-72089-5_25"},{"issue":"3","key":"17_CR28","doi-asserted-by":"publisher","first-page":"187","DOI":"10.20517\/ais.2024.12","volume":"4","author":"R Wei","year":"2024","unstructured":"Wei, R., et al.: Scale-aware monocular reconstruction via robot kinematics and visual data in neural radiance fields. Artificial Intelligence Surgery 4(3), 187\u2013198 (2024)","journal-title":"Artificial Intelligence Surgery"},{"key":"17_CR29","doi-asserted-by":"crossref","unstructured":"S. Chen et al.: Video depth anything: Consistent depth estimation for super-long videos. arXiv preprint arXiv:2501.12375 (2025)","DOI":"10.1109\/CVPR52734.2025.02126"},{"key":"17_CR30","doi-asserted-by":"crossref","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)","DOI":"10.1016\/j.media.2021.102338"},{"key":"17_CR31","doi-asserted-by":"crossref","unstructured":"S. Wang et al.: Dust3r: Geometric 3d vision made easy. In: CVPR. pp. 20697\u201320709 (2024)","DOI":"10.1109\/CVPR52733.2024.01956"},{"key":"17_CR32","doi-asserted-by":"crossref","unstructured":"T. Bobrow et al.: Colonoscopy 3d video dataset with paired depth from 2d-3d registration. Medical Image Analysis p. 102956 (2023)","DOI":"10.1016\/j.media.2023.102956"},{"key":"17_CR33","doi-asserted-by":"crossref","unstructured":"X. Gu et al.: Cascade cost volume for high-resolution multi-view stereo and stereo matching. In: CVPR. pp. 2495\u20132504 (2020)","DOI":"10.1109\/CVPR42600.2020.00257"},{"key":"17_CR34","unstructured":"X. Guo et al.: Stereo anything: Unifying stereo matching with large-scale mixed data. arXiv preprint arXiv:2411.14053 (2024)"},{"key":"17_CR35","doi-asserted-by":"crossref","unstructured":"Y. Lu et al.: Autonomous intelligent navigation for flexible endoscopy using monocular depth guidance and 3-d shape planning. In: ICRA. pp.\u00a01\u20137. IEEE (2023)","DOI":"10.1109\/ICRA48891.2023.10161505"},{"key":"17_CR36","doi-asserted-by":"crossref","unstructured":"Y. Yao et al.: Mvsnet: Depth inference for unstructured multi-view stereo. In: ECCV. pp. 767\u2013783 (2018)","DOI":"10.1007\/978-3-030-01237-3_47"},{"key":"17_CR37","doi-asserted-by":"crossref","unstructured":"Z. Teed et al.: Raft: Recurrent all-pairs field transforms for optical flow. In: ECCV. pp. 402\u2013419. Springer (2020)","DOI":"10.1007\/978-3-030-58536-5_24"},{"key":"17_CR38","first-page":"16558","volume":"34","author":"Z Teed","year":"2021","unstructured":"Teed, Z., et al.: Droid-slam: Deep visual slam for monocular, stereo, and rgb-d cameras. Adv. Neural. Inf. Process. Syst. 34, 16558\u201316569 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"17_CR39","doi-asserted-by":"crossref","unstructured":"Z. Wang et al.: Autolaparo: A new dataset of integrated multi-tasks for image-guided surgical automation in laparoscopic hysterectomy. In: MICCAI. pp. 486\u2013496 (2022)","DOI":"10.1007\/978-3-031-16449-1_46"}],"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\/978-3-032-05114-1_17","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,20]],"date-time":"2025-09-20T14:10:29Z","timestamp":1758377429000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-05114-1_17"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,21]]},"ISBN":["9783032051134","9783032051141"],"references-count":39,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-05114-1_17","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,9,21]]},"assertion":[{"value":"21 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"}}]}}