{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,5]],"date-time":"2026-10-05T14:58:05Z","timestamp":1791212285408,"version":"4.1.0"},"reference-count":38,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62471122"],"award-info":[{"award-number":["62471122"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["clinicalkey.com","clinicalkey.com.au","clinicalkey.es","clinicalkey.fr","clinicalkey.jp","elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Computerized Medical Imaging and Graphics"],"published-print":{"date-parts":[[2026,10]]},"DOI":"10.1016\/j.compmedimag.2026.102824","type":"journal-article","created":{"date-parts":[[2026,9,23]],"date-time":"2026-09-23T14:59:18Z","timestamp":1790175558000},"page":"102824","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["RC-EndoDepth: Two-stage self-supervised depth and motion estimation with improved scale consistency in endoscopic videos"],"prefix":"10.1016","volume":"135","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-4201-4541","authenticated-orcid":false,"given":"Juntao","family":"Han","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mingxiao","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ziming","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wenjun","family":"Tan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yufei","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.compmedimag.2026.102824_b1","series-title":"Stereo correspondence and reconstruction of endoscopic data challenge","author":"Allan","year":"2021"},{"key":"10.1016\/j.compmedimag.2026.102824_b2","article-title":"Monocular depth estimation: A thorough review","author":"Arampatzakis","year":"2023","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.compmedimag.2026.102824_b3","article-title":"Unsupervised scale-consistent depth and ego-motion learning from monocular video","volume":"32","author":"Bian","year":"2019","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.compmedimag.2026.102824_b4","doi-asserted-by":"crossref","DOI":"10.1016\/j.media.2023.102956","article-title":"Colonoscopy 3D video dataset with paired depth from 2D-3D registration","volume":"90","author":"Bobrow","year":"2023","journal-title":"Med. Image Anal."},{"key":"10.1016\/j.compmedimag.2026.102824_b5","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"22831","article-title":"Video depth anything: Consistent depth estimation for super-long videos","author":"Chen","year":"2025"},{"issue":"1","key":"10.1016\/j.compmedimag.2026.102824_b6","doi-asserted-by":"crossref","first-page":"371","DOI":"10.1109\/TMI.2020.3027442","article-title":"Augmented reality guided laparoscopic surgery of the uterus","volume":"40","author":"Collins","year":"2020","journal-title":"IEEE Trans. Med. Imaging"},{"key":"10.1016\/j.compmedimag.2026.102824_b7","doi-asserted-by":"crossref","DOI":"10.1007\/s11548-024-03083-5","article-title":"Surgical-DINO: Adapter learning of foundation models for depth estimation in endoscopic surgery","author":"Cui","year":"2024","journal-title":"Int. J. Comput. Assist. Radiol. Surg."},{"key":"10.1016\/j.compmedimag.2026.102824_b8","series-title":"International Conference on Medical Image Computing and Computer-Assisted Intervention","article-title":"EndoDAC: Efficient adapting foundation model for self-supervised depth estimation from any endoscopic camera","author":"Cui","year":"2024"},{"key":"10.1016\/j.compmedimag.2026.102824_b9","unstructured":"Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., Gelly, S., Uszkoreit, J., Houlsby, N., 2021b. An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale. In: International Conference on Learning Representations. ICLR."},{"key":"10.1016\/j.compmedimag.2026.102824_b10","doi-asserted-by":"crossref","DOI":"10.1016\/j.media.2021.102302","article-title":"SERV-CT: A disparity dataset from cone-beam CT for validation of endoscopic 3D reconstruction","volume":"76","author":"Edwards","year":"2022","journal-title":"Med. Image Anal."},{"key":"10.1016\/j.compmedimag.2026.102824_b11","series-title":"Neural Information Processing Systems","article-title":"Depth map prediction from a single image using a multi-scale deep network","author":"Eigen","year":"2014"},{"key":"10.1016\/j.compmedimag.2026.102824_b12","doi-asserted-by":"crossref","unstructured":"Geiger, A., Lenz, P., Urtasun, R., 2012. Are we ready for Autonomous Driving? The KITTI Vision Benchmark Suite. In: Conference on Computer Vision and Pattern Recognition. CVPR.","DOI":"10.1109\/CVPR.2012.6248074"},{"key":"10.1016\/j.compmedimag.2026.102824_b13","doi-asserted-by":"crossref","unstructured":"Godard, C., Mac Aodha, O., Firman, M., Brostow, G.J., 2019. Digging into self-supervised monocular depth estimation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision. pp. 3828\u20133838.","DOI":"10.1109\/ICCV.2019.00393"},{"issue":"1","key":"10.1016\/j.compmedimag.2026.102824_b14","doi-asserted-by":"crossref","first-page":"135","DOI":"10.1109\/TMI.2013.2282997","article-title":"Visual SLAM for handheld monocular endoscope","volume":"33","author":"Grasa","year":"2013","journal-title":"IEEE Trans. Med. Imaging"},{"key":"10.1016\/j.compmedimag.2026.102824_b15","doi-asserted-by":"crossref","unstructured":"Guo, J., Dong, W., Huang, T., Ding, H., Wang, Z., Kuang, H., Dou, Q., Liu, Y.-H., 2025. Endo3R: Unified Online Reconstruction from Dynamic Monocular Endoscopic Video. In: Medical Image Computing and Computer Assisted Intervention \u2013 MICCAI 2025. pp. 177\u2013186.","DOI":"10.1007\/978-3-032-05114-1_17"},{"key":"10.1016\/j.compmedimag.2026.102824_b16","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J., 2016. Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. pp. 770\u2013778.","DOI":"10.1109\/CVPR.2016.90"},{"key":"10.1016\/j.compmedimag.2026.102824_b17","unstructured":"Hu, E.J., Shen, Y., Wallis, P., Allen-Zhu, Z., Li, Y., Wang, S., Wang, L., Chen, W., 2022. LoRA: Low-Rank Adaptation of Large Language Models. In: International Conference on Learning Representations."},{"key":"10.1016\/j.compmedimag.2026.102824_b18","unstructured":"Kingma, D.P., Ba, J., 2015. Adam: A Method for Stochastic Optimization. In: International Conference on Learning Representations. ICLR."},{"key":"10.1016\/j.compmedimag.2026.102824_b19","article-title":"Image intrinsic-based unsupervised monocular depth estimation in endoscopy","author":"Li","year":"2024","journal-title":"IEEE J. Biomed. Health Inform."},{"key":"10.1016\/j.compmedimag.2026.102824_b20","doi-asserted-by":"crossref","DOI":"10.1016\/j.compmedimag.2026.102734","article-title":"Scale-consistent 3D reconstruction in monocular colonoscopy via camera-intrinsics-guided learning","volume":"129","author":"Liu","year":"2026","journal-title":"Comput. Med. Imaging Graph."},{"issue":"4","key":"10.1016\/j.compmedimag.2026.102824_b21","doi-asserted-by":"crossref","DOI":"10.1145\/3386569.3392377","article-title":"Consistent video depth estimation","volume":"39","author":"Luo","year":"2020","journal-title":"ACM Trans. Graph."},{"key":"10.1016\/j.compmedimag.2026.102824_b22","doi-asserted-by":"crossref","DOI":"10.1016\/j.compmedimag.2025.102616","article-title":"Surgical augmented reality registration methods: A review from traditional to deep learning approaches","volume":"124","author":"Neri","year":"2025","journal-title":"Comput. Med. Imaging Graph."},{"key":"10.1016\/j.compmedimag.2026.102824_b23","doi-asserted-by":"crossref","DOI":"10.1016\/j.compmedimag.2024.102418","article-title":"2D\/3D deformable registration for endoscopic camera images using self-supervised offline learning of intraoperative pneumothorax deformation","volume":"116","author":"Oya","year":"2024","journal-title":"Comput. Med. Imaging Graph."},{"key":"10.1016\/j.compmedimag.2026.102824_b24","doi-asserted-by":"crossref","DOI":"10.1016\/j.media.2021.102058","article-title":"EndoSLAM dataset and an unsupervised monocular visual odometry and depth estimation approach for endoscopic videos","volume":"71","author":"Ozyoruk","year":"2021","journal-title":"Med. Image Anal."},{"key":"10.1016\/j.compmedimag.2026.102824_b25","series-title":"Advances in Neural Information Processing Systems (NeurIPS)","article-title":"Pytorch: An imperative style, high-performance deep learning library","author":"Paszke","year":"2019"},{"key":"10.1016\/j.compmedimag.2026.102824_b26","doi-asserted-by":"crossref","unstructured":"Ranftl, R., Bochkovskiy, A., Koltun, V., 2021. Vision transformers for dense prediction. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision. pp. 12179\u201312188.","DOI":"10.1109\/ICCV48922.2021.01196"},{"key":"10.1016\/j.compmedimag.2026.102824_b27","doi-asserted-by":"crossref","first-page":"83","DOI":"10.1016\/j.compbiomed.2015.09.021","article-title":"Fuzzy zoning for feature matching technique in 3D reconstruction of nasal endoscopic images","volume":"67","author":"Rattanalappaiboon","year":"2015","journal-title":"Comput. Biol. Med."},{"key":"10.1016\/j.compmedimag.2026.102824_b28","series-title":"Proceedings IEEE Workshop on Stereo and Multi-Baseline Vision (SMBV 2001)","first-page":"131","article-title":"A taxonomy and evaluation of dense two-frame stereo correspondence algorithms","author":"Scharstein","year":"2001"},{"key":"10.1016\/j.compmedimag.2026.102824_b29","doi-asserted-by":"crossref","DOI":"10.1016\/j.media.2021.102338","article-title":"Self-supervised monocular depth and ego-motion estimation in endoscopy: Appearance flow to the rescue","volume":"77","author":"Shao","year":"2022","journal-title":"Med. Image Anal."},{"key":"10.1016\/j.compmedimag.2026.102824_b30","series-title":"Medical Image Computing and Computer Assisted Intervention \u2013 MICCAI 2025","first-page":"117","article-title":"Endo-FASt3r: Endoscopic foundation model adaptation for structure from motion","author":"Sheikh Zeinoddin","year":"2025"},{"key":"10.1016\/j.compmedimag.2026.102824_b31","doi-asserted-by":"crossref","DOI":"10.1016\/j.compmedimag.2025.102640","article-title":"Accurate and fast monocular endoscopic depth estimation of structure-content integrated diffusion","volume":"125","author":"Tan","year":"2025","journal-title":"Comput. Med. Imaging Graph."},{"key":"10.1016\/j.compmedimag.2026.102824_b32","series-title":"2018 IEEE\/RSJ International Conference on Intelligent Robots and Systems","first-page":"1801","article-title":"Unsupervised odometry and depth learning for endoscopic capsule robots","author":"Turan","year":"2018"},{"issue":"4","key":"10.1016\/j.compmedimag.2026.102824_b33","doi-asserted-by":"crossref","first-page":"600","DOI":"10.1109\/TIP.2003.819861","article-title":"Image quality assessment: from error visibility to structural similarity","volume":"13","author":"Wang","year":"2004","journal-title":"IEEE Trans. Image Process."},{"key":"10.1016\/j.compmedimag.2026.102824_b34","series-title":"Self-supervised monocular depth and pose estimation for endoscopy with generative latent priors","author":"Xu","year":"2024"},{"key":"10.1016\/j.compmedimag.2026.102824_b35","series-title":"Depth any video with scalable synthetic data","author":"Yang","year":"2024"},{"key":"10.1016\/j.compmedimag.2026.102824_b36","doi-asserted-by":"crossref","first-page":"3449","DOI":"10.1007\/s00464-019-07121-1","article-title":"Real-time navigation for laparoscopic hepatectomy using image fusion of preoperative 3D surgical plan and intraoperative indocyanine green fluorescence imaging","volume":"34","author":"Zhang","year":"2020","journal-title":"Surg. Endosc."},{"key":"10.1016\/j.compmedimag.2026.102824_b37","doi-asserted-by":"crossref","unstructured":"Zhang, N., Nex, F., Vosselman, G., Kerle, N., 2023. Lite-mono: A lightweight cnn and transformer architecture for self-supervised monocular depth estimation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 18537\u201318546.","DOI":"10.1109\/CVPR52729.2023.01778"},{"key":"10.1016\/j.compmedimag.2026.102824_b38","doi-asserted-by":"crossref","unstructured":"Zhou, T., Brown, M., Snavely, N., Lowe, D.G., 2017. Unsupervised learning of depth and ego-motion from video. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. pp. 1851\u20131858.","DOI":"10.1109\/CVPR.2017.700"}],"container-title":["Computerized Medical Imaging and Graphics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0895611126001278?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0895611126001278?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,10,5]],"date-time":"2026-10-05T14:48:53Z","timestamp":1791211733000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0895611126001278"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,10]]},"references-count":38,"alternative-id":["S0895611126001278"],"URL":"https:\/\/doi.org\/10.1016\/j.compmedimag.2026.102824","relation":{},"ISSN":["0895-6111"],"issn-type":[{"value":"0895-6111","type":"print"}],"subject":[],"published":{"date-parts":[[2026,10]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"RC-EndoDepth: Two-stage self-supervised depth and motion estimation with improved scale consistency in endoscopic videos","name":"articletitle","label":"Article Title"},{"value":"Computerized Medical Imaging and Graphics","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.compmedimag.2026.102824","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier Ltd. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"102824"}}