{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,18]],"date-time":"2026-07-18T17:56:11Z","timestamp":1784397371179,"version":"3.55.0"},"publisher-location":"Cham","reference-count":33,"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_20","type":"book-chapter","created":{"date-parts":[[2024,10,2]],"date-time":"2024-10-02T16:02:20Z","timestamp":1727884940000},"page":"208-218","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":47,"title":["EndoDAC: Efficient Adapting Foundation Model for\u00a0Self-Supervised Depth Estimation from\u00a0Any Endoscopic Camera"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-7900-8032","authenticated-orcid":false,"given":"Beilei","family":"Cui","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7162-2822","authenticated-orcid":false,"given":"Mobarakol","family":"Islam","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9762-6821","authenticated-orcid":false,"given":"Long","family":"Bai","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5515-0653","authenticated-orcid":false,"given":"An","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6488-1551","authenticated-orcid":false,"given":"Hongliang","family":"Ren","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,10,3]]},"reference":[{"key":"20_CR1","doi-asserted-by":"crossref","unstructured":"Arampatzakis, V., Pavlidis, G., Mitianoudis, N., Papamarkos, N.: Monocular depth estimation: A thorough review. IEEE Transactions on Pattern Analysis and Machine Intelligence (2023)","DOI":"10.1109\/TPAMI.2023.3330944"},{"key":"20_CR2","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":"20_CR3","unstructured":"Bian, J., Li, Z., Wang, N., Zhan, H., Shen, C., Cheng, M.M., Reid, I.: Unsupervised scale-consistent depth and ego-motion learning from monocular video. Advances in neural information processing systems 32 (2019)"},{"key":"20_CR4","doi-asserted-by":"crossref","unstructured":"Chen, T., Zhu, L., Ding, C., Cao, R., Zhang, S., Wang, Y., Li, Z., Sun, L., Mao, P., Zang, Y.: Sam fails to segment anything?\u2013sam-adapter: Adapting sam in underperformed scenes: Camouflage, shadow, and more. arXiv preprint arXiv:2304.09148 (2023)","DOI":"10.1109\/ICCVW60793.2023.00361"},{"issue":"1","key":"20_CR5","doi-asserted-by":"publisher","first-page":"371","DOI":"10.1109\/TMI.2020.3027442","volume":"40","author":"T Collins","year":"2020","unstructured":"Collins, T., Pizarro, D., Gasparini, S., Bourdel, N., Chauvet, P., Canis, M., Calvet, L., Bartoli, A.: Augmented reality guided laparoscopic surgery of the uterus. IEEE Transactions on Medical Imaging 40(1), 371\u2013380 (2020)","journal-title":"IEEE Transactions on Medical Imaging"},{"key":"20_CR6","doi-asserted-by":"crossref","unstructured":"Cui, B., Islam, M., Bai, L., Ren, H.: Surgical-dino: Adapter learning of foundation model for depth estimation in endoscopic surgery. arXiv preprint arXiv:2401.06013 (2024)","DOI":"10.1007\/s11548-024-03083-5"},{"key":"20_CR7","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":"20_CR8","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":"20_CR9","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":"20_CR10","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 transactions on medical imaging 33(1), 135\u2013146 (2013)","journal-title":"IEEE transactions on medical imaging"},{"key":"20_CR11","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition. pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"20_CR12","unstructured":"Hu, E.J., yelong shen, Wallis, P., Allen-Zhu, Z., Li, Y., Wang, S., Wang, L., Chen, W.: LoRA: Low-rank adaptation of large language models. In: International Conference on Learning Representations (2022)"},{"key":"20_CR13","doi-asserted-by":"crossref","unstructured":"Huang, Y., Cui, B., Bai, L., Guo, Z., Xu, M., Ren, H.: Endo-4dgs: Distilling depth ranking for endoscopic monocular scene reconstruction with 4d gaussian splatting. arXiv preprint arXiv:2401.16416 (2024)","DOI":"10.1007\/978-3-031-72089-5_19"},{"key":"20_CR14","doi-asserted-by":"crossref","unstructured":"Kirillov, A., Mintun, E., Ravi, N., Mao, H., Rolland, C., Gustafson, L., Xiao, T., Whitehead, S., Berg, A.C., Lo, W.Y., et\u00a0al.: Segment anything. arXiv preprint arXiv:2304.02643 (2023)","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"20_CR15","unstructured":"Loshchilov, I., Hutter, F.: Decoupled weight decay regularization. In: International Conference on Learning Representations (2019)"},{"key":"20_CR16","unstructured":"Oquab, M., Darcet, T., Moutakanni, T., Vo, H., Szafraniec, M., Khalidov, V., Fernandez, P., Haziza, D., Massa, F., El-Nouby, A., et\u00a0al.: Dinov2: Learning robust visual features without supervision. arXiv preprint arXiv:2304.07193 (2023)"},{"key":"20_CR17","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":"20_CR18","unstructured":"Park, N., Kim, S.: How do vision transformers work? In: International Conference on Learning Representations (2021)"},{"key":"20_CR19","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":"20_CR20","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. Computers in Biology and Medicine 67, 83\u201394 (2015)","journal-title":"Computers in Biology and Medicine"},{"issue":"4","key":"20_CR21","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":"20_CR22","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":"20_CR23","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":"20_CR24","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 Transactions on Pattern Analysis and Machine Intelligence (2023)","DOI":"10.1109\/TPAMI.2023.3322549"},{"key":"20_CR25","doi-asserted-by":"crossref","unstructured":"Wang, A., Islam, M., Xu, M., Zhang, Y., Ren, H.: Sam meets robotic surgery: An empirical study in robustness perspective. arXiv preprint arXiv:2304.14674 (2023)","DOI":"10.1007\/978-3-031-47401-9_23"},{"issue":"4","key":"20_CR26","doi-asserted-by":"publisher","first-page":"600","DOI":"10.1109\/TIP.2003.819861","volume":"13","author":"Z Wang","year":"2004","unstructured":"Wang, Z., Bovik, A.C., Sheikh, H.R., Simoncelli, E.P.: Image quality assessment: from error visibility to structural similarity. IEEE transactions on image processing 13(4), 600\u2013612 (2004)","journal-title":"IEEE transactions on image processing"},{"key":"20_CR27","doi-asserted-by":"crossref","unstructured":"Wu, Q., Zhang, Y., Elbatel, M.: Self-prompting large vision models for few-shot medical image segmentation. In: MICCAI Workshop on Domain Adaptation and Representation Transfer. pp. 156\u2013167. Springer (2023)","DOI":"10.1007\/978-3-031-45857-6_16"},{"key":"20_CR28","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. arXiv preprint arXiv:2401.10891 (2024)","DOI":"10.1109\/CVPR52733.2024.00987"},{"key":"20_CR29","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"},{"key":"20_CR30","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2023.102091","volume":"103","author":"J Yao","year":"2024","unstructured":"Yao, J., Wang, X., Yang, S., Wang, B.: Vitmatte: Boosting image matting with pre-trained plain vision transformers. Information Fusion 103, 102091 (2024)","journal-title":"Information Fusion"},{"key":"20_CR31","doi-asserted-by":"crossref","unstructured":"Zhang, K., Liu, D.: Customized segment anything model for medical image segmentation. arXiv preprint arXiv:2304.13785 (2023)","DOI":"10.2139\/ssrn.4495221"},{"key":"20_CR32","doi-asserted-by":"publisher","first-page":"3449","DOI":"10.1007\/s00464-019-07121-1","volume":"34","author":"P Zhang","year":"2020","unstructured":"Zhang, P., Luo, H., Zhu, W., Yang, J., Zeng, N., Fan, Y., Wen, S., Xiang, N., Jia, F., Fang, C.: Real-time navigation for laparoscopic hepatectomy using image fusion of preoperative 3d surgical plan and intraoperative indocyanine green fluorescence imaging. Surgical endoscopy 34, 3449\u20133459 (2020)","journal-title":"Surgical endoscopy"},{"key":"20_CR33","doi-asserted-by":"crossref","unstructured":"Zhou, T., Brown, M., Snavely, N., Lowe, D.G.: Unsupervised learning of depth and ego-motion from video. In: Proceedings of the IEEE conference on computer vision and pattern recognition. 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 2024"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-72089-5_20","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,29]],"date-time":"2024-11-29T00:41:16Z","timestamp":1732840876000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-72089-5_20"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"ISBN":["9783031720888","9783031720895"],"references-count":33,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-72089-5_20","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.","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"}}]}}