{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T17:54:02Z","timestamp":1775066042135,"version":"3.50.1"},"publisher-location":"Cham","reference-count":32,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031919787","type":"print"},{"value":"9783031919794","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"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":[[2025]]},"DOI":"10.1007\/978-3-031-91979-4_1","type":"book-chapter","created":{"date-parts":[[2025,5,31]],"date-time":"2025-05-31T19:07:32Z","timestamp":1748718452000},"page":"1-11","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["DARES: Depth Anything in\u00a0Robotic Endoscopic Surgery with\u00a0Self-supervised Vector-LoRA of\u00a0the\u00a0Foundation Model"],"prefix":"10.1007","author":[{"given":"Mona","family":"Sheikh Zeinoddin","sequence":"first","affiliation":[]},{"given":"Chiara","family":"Lena","sequence":"additional","affiliation":[]},{"given":"Jiongqi","family":"Qu","sequence":"additional","affiliation":[]},{"given":"Luca","family":"Carlini","sequence":"additional","affiliation":[]},{"given":"Mattia","family":"Magro","sequence":"additional","affiliation":[]},{"given":"Seunghoi","family":"Kim","sequence":"additional","affiliation":[]},{"given":"Elena","family":"De Momi","sequence":"additional","affiliation":[]},{"given":"Sophia","family":"Bano","sequence":"additional","affiliation":[]},{"given":"Matthew","family":"Grech-Sollars","sequence":"additional","affiliation":[]},{"given":"Evangelos","family":"Mazomenos","sequence":"additional","affiliation":[]},{"given":"Daniel C.","family":"Alexander","sequence":"additional","affiliation":[]},{"given":"Danail","family":"Stoyanov","sequence":"additional","affiliation":[]},{"given":"Matthew J.","family":"Clarkson","sequence":"additional","affiliation":[]},{"given":"Mobarakol","family":"Islam","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,5,12]]},"reference":[{"key":"1_CR1","unstructured":"Allan, M., et\u00a0al.: Stereo correspondence and reconstruction of endoscopic data challenge. arXiv preprint arXiv:2101.01133 (2021)"},{"key":"1_CR2","unstructured":"Bian, J., et al.: Unsupervised scale-consistent depth and ego-motion learning from monocular video. Adv. Neural Inf. Process. Syst. 32 (2019)"},{"issue":"3","key":"1_CR3","doi-asserted-by":"publisher","first-page":"171","DOI":"10.1038\/s41575-022-00701-y","volume":"20","author":"F Chadebecq","year":"2023","unstructured":"Chadebecq, F., Lovat, L.B., Stoyanov, D.: Artificial intelligence and automation in endoscopy and surgery. Nat. Rev. Gastroenterol. Hepatol. 20(3), 171\u2013182 (2023)","journal-title":"Nat. Rev. Gastroenterol. Hepatol."},{"key":"1_CR4","volume":"6","author":"J Chai","year":"2021","unstructured":"Chai, J., Zeng, H., Li, A., Ngai, E.W.: Deep learning in computer vision: a critical review of emerging techniques and application scenarios. Mach. Learn. Appl. 6, 100134 (2021)","journal-title":"Mach. Learn. Appl."},{"key":"1_CR5","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":"1_CR6","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. International Journal of Computer Assisted Radiology and Surgery (2024)","DOI":"10.1007\/s11548-024-03083-5"},{"key":"1_CR7","unstructured":"Dosovitskiy, A., et al.: An image is worth 16x16 words: Transformers for image recognition at scale. ICLR (2021)"},{"key":"1_CR8","unstructured":"Eigen, D., Puhrsch, C., Fergus, R.: Depth map prediction from a single image using a multi-scale deep network. In: Proceedings of the 27th International Conference on Neural Information Processing Systems - Volume 2, pp. 2366\u20132374. NIPS\u201914, MIT Press, Cambridge, MA, USA (2014)"},{"key":"1_CR9","doi-asserted-by":"crossref","unstructured":"Florea, H., Miclea, V.C., Nedevschi, S.: WildUAV: monocular UAV dataset for depth estimation tasks. In: 2021 IEEE 17th International Conference on Intelligent Computer Communication and Processing (ICCP), pp. 291\u2013298. IEEE (2021)","DOI":"10.1109\/ICCP53602.2021.9733671"},{"issue":"4","key":"1_CR10","doi-asserted-by":"publisher","first-page":"128","DOI":"10.1016\/S1364-6613(99)01294-2","volume":"3","author":"RM French","year":"1999","unstructured":"French, R.M.: Catastrophic forgetting in connectionist networks. Trends Cogn. Sci. 3(4), 128\u2013135 (1999)","journal-title":"Trends Cogn. Sci."},{"key":"1_CR11","doi-asserted-by":"crossref","unstructured":"Fu, J., et al.: Recent advancements in augmented reality for robotic applications: a survey. Actuators 12(8) (2023)","DOI":"10.3390\/act12080323"},{"key":"1_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":"1_CR13","unstructured":"Hu, E.J., et al.: LoRA: low-rank adaptation of large language models. In: International Conference on Learning Representations (2022)"},{"key":"1_CR14","unstructured":"Jiang, T., et\u00a0al.: MoRA: High-rank updating for parameter-efficient fine-tuning. arXiv preprint arXiv:2405.12130 (2024)"},{"key":"1_CR15","unstructured":"Luo, Y., Yang, Z., Meng, F., Li, Y., Zhou, J., Zhang, Y.: An empirical study of catastrophic forgetting in large language models during continual fine-tuning. arXiv preprint arXiv:2308.08747 (2023)"},{"key":"1_CR16","unstructured":"Oquab, M., et\u00a0al.: DINOv2: Learning robust visual features without supervision. arXiv preprint arXiv:2304.07193 (2023)"},{"key":"1_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":"4","key":"1_CR18","first-page":"161","volume":"6","author":"L Privitera","year":"2022","unstructured":"Privitera, L., Paraboschi, I., Dixit, D., Arthurs, O.J., Giuliani, S.: Image-guided surgery and novel intraoperative devices for enhanced visualisation in general and paediatric surgery: a review. Innovative Surg. Sci. 6(4), 161\u2013172 (2022)","journal-title":"Innovative Surg. Sci."},{"key":"1_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":"1_CR20","doi-asserted-by":"crossref","unstructured":"Shao, S., et al.: Self-supervised learning for monocular depth estimation on minimally invasive surgery scenes. In: 2021 IEEE International Conference on Robotics and Automation (ICRA), pp. 7159\u20137165. IEEE (2021)","DOI":"10.1109\/ICRA48506.2021.9561508"},{"key":"1_CR21","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":"1_CR22","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"},{"issue":"20","key":"1_CR23","doi-asserted-by":"publisher","first-page":"8503","DOI":"10.3390\/s23208503","volume":"23","author":"T Wang","year":"2023","unstructured":"Wang, T., Li, H., Pu, T., Yang, L.: Microsurgery robots: applications, design, and development. Sensors 23(20), 8503 (2023)","journal-title":"Sensors"},{"issue":"4","key":"1_CR24","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 Trans. Image Process. 13(4), 600\u2013612 (2004)","journal-title":"IEEE Trans. Image Process."},{"key":"1_CR25","unstructured":"Wang, Z., Simoncelli, E.P., Bovik, A.C.: Multiscale structural similarity for image quality assessment. In: The Thrity-Seventh Asilomar Conference on Signals, Systems & Computers, 2003. vol.\u00a02, pp. 1398\u20131402. IEEE (2003)"},{"key":"1_CR26","doi-asserted-by":"crossref","unstructured":"Wei, R., et al.: Absolute monocular depth estimation on robotic visual and kinematics data via self-supervised learning. IEEE Transactions on Automation Science and Engineering (2024)","DOI":"10.1109\/TASE.2024.3409392"},{"key":"1_CR27","unstructured":"Wu, J., et al.: Medical SAM adapter: Adapting segment anything model for medical image segmentation. arXiv preprint arXiv:2304.12620 (2023)"},{"key":"1_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. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10371\u201310381 (2024)","DOI":"10.1109\/CVPR52733.2024.00987"},{"key":"1_CR29","unstructured":"Yang, L., et al.: Depth anything V2. arXiv preprint arXiv:2406.09414 (2024)"},{"key":"1_CR30","doi-asserted-by":"crossref","unstructured":"Yang, Z., Dai, J., Pan, J.: 3D reconstruction from endoscopy images: a survey. Comput. Biol. Med. 108546 (2024)","DOI":"10.1016\/j.compbiomed.2024.108546"},{"key":"1_CR31","unstructured":"Zhao, J., Zhang, Z., Chen, B., Wang, Z., Anandkumar, A., Tian, Y.: GaLore: Memory-efficient LLM training by gradient low-rank projection. arXiv preprint arXiv:2403.03507 (2024)"},{"key":"1_CR32","doi-asserted-by":"crossref","unstructured":"Zhou, T., Brown, M., Snavely, N., Lowe, D.G.: Unsupervised learning of depth and ego-motion from video. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 6612\u20136619 (2017)","DOI":"10.1109\/CVPR.2017.700"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2024 Workshops"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-91979-4_1","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,31]],"date-time":"2025-05-31T19:07:40Z","timestamp":1748718460000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-91979-4_1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9783031919787","9783031919794"],"references-count":32,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-91979-4_1","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]},"assertion":[{"value":"12 May 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Milan","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Italy","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":"29 September 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 October 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2024.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}