{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,3]],"date-time":"2026-06-03T14:10:10Z","timestamp":1780495810755,"version":"3.54.1"},"reference-count":47,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100003399","name":"Science and Technology Commission of Shanghai Municipality","doi-asserted-by":"publisher","award":["2021SHZDZX"],"award-info":[{"award-number":["2021SHZDZX"]}],"id":[{"id":"10.13039\/501100003399","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62203296"],"award-info":[{"award-number":["62203296"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Pattern Recognition"],"published-print":{"date-parts":[[2026,11]]},"DOI":"10.1016\/j.patcog.2026.113510","type":"journal-article","created":{"date-parts":[[2026,3,17]],"date-time":"2026-03-17T15:59:22Z","timestamp":1773763162000},"page":"113510","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"PA","title":["Simultaneous surgical stereo depth and motion estimation via brightness-aware self-supervised learning"],"prefix":"10.1016","volume":"179","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2431-2653","authenticated-orcid":false,"given":"Yuxuan","family":"Liu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-9131-7738","authenticated-orcid":false,"given":"Xinyao","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-6050-4106","authenticated-orcid":false,"given":"Yating","family":"Luo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-9810-6272","authenticated-orcid":false,"given":"Yunfei","family":"Luan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-6626-2831","authenticated-orcid":false,"given":"Zhennan","family":"Xiao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8041-1245","authenticated-orcid":false,"given":"Yao","family":"Guo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4060-4020","authenticated-orcid":false,"given":"Guang-Zhong","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"issue":"60","key":"10.1016\/j.patcog.2026.113510_bib0001","article-title":"A decade retrospective of medical robotics research from 2010 to 2020","volume":"6","author":"Dupont","year":"2021","journal-title":"Sci. Rob."},{"issue":"104","key":"10.1016\/j.patcog.2026.113510_bib0002","article-title":"Surgical embodied intelligence for generalized task autonomy in laparoscopic robot-assisted surgery","volume":"10","author":"Long","year":"2025","journal-title":"Sci. Rob."},{"issue":"104","key":"10.1016\/j.patcog.2026.113510_bib0003","article-title":"SRT-H: a hierarchical framework for autonomous surgery via language-conditioned imitation learning","volume":"10","author":"Kim","year":"2025","journal-title":"Sci. Rob."},{"issue":"2","key":"10.1016\/j.patcog.2026.113510_bib0004","doi-asserted-by":"crossref","first-page":"400","DOI":"10.1109\/TMI.2019.2927436","article-title":"Real-time dense reconstruction of tissue surface from stereo optical video","volume":"39","author":"Zhou","year":"2019","journal-title":"IEEE Trans. Med. Imaging"},{"key":"10.1016\/j.patcog.2026.113510_bib0005","series-title":"International Conference on Medical Image Computing and Computer-Assisted Intervention","first-page":"42","article-title":"Real-time dense stereo reconstruction using convex optimisation with a cost-volume for image-guided robotic surgery","author":"Chang","year":"2013"},{"key":"10.1016\/j.patcog.2026.113510_bib0006","doi-asserted-by":"crossref","first-page":"197","DOI":"10.1007\/s11548-015-1276-0","article-title":"Dense soft tissue 3D reconstruction refined with super-pixel segmentation for robotic abdominal surgery","volume":"11","author":"Penza","year":"2016","journal-title":"Int. J. Comput. Assist. Radiol. Surg."},{"key":"10.1016\/j.patcog.2026.113510_bib0007","doi-asserted-by":"crossref","DOI":"10.1016\/j.media.2023.102994","article-title":"A temporal learning approach to inpainting endoscopic specularities and its effect on image correspondence","volume":"90","author":"Daher","year":"2023","journal-title":"Med. Image Anal."},{"issue":"9","key":"10.1016\/j.patcog.2026.113510_bib0008","doi-asserted-by":"crossref","first-page":"6547","DOI":"10.1109\/TVCG.2023.3347438","article-title":"A self-supervised network-based smoke removal and depth estimation for monocular endoscopic videos","volume":"30","author":"Zhang","year":"2024","journal-title":"IEEE Trans. Vis. Comput. Graph."},{"key":"10.1016\/j.patcog.2026.113510_bib0009","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2025.112724","article-title":"NEPose: a novel benchmark dataset with an improved framework for vision-based nasal endoscope pose estimation","volume":"172","author":"Shao","year":"2026","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.113510_bib0010","doi-asserted-by":"crossref","DOI":"10.1016\/j.media.2025.103698","article-title":"FPM-R2Net: fused photoacoustic and operating microscopic imaging with cross-modality representation and registration network","volume":"105","author":"Liu","year":"2025","journal-title":"Med. Image Anal."},{"key":"10.1016\/j.patcog.2026.113510_bib0011","series-title":"Proceedings of the Computer Vision and Pattern Recognition Conference","first-page":"5294","article-title":"VGGT: visual geometry grounded transformer","author":"Wang","year":"2025"},{"key":"10.1016\/j.patcog.2026.113510_bib0012","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2025.112179","article-title":"SegMIC: a universal model for medical image segmentation through in-context learning","volume":"171","author":"Zhao","year":"2026","journal-title":"Pattern Recognit."},{"issue":"11","key":"10.1016\/j.patcog.2026.113510_bib0013","doi-asserted-by":"crossref","first-page":"3269","DOI":"10.1109\/TMI.2023.3279899","article-title":"Bidirectional semi-supervised dual-branch CNN for robust 3D reconstruction of stereo endoscopic images via adaptive cross and parallel supervisions","volume":"42","author":"Shi","year":"2023","journal-title":"IEEE Trans. Med. Imaging"},{"key":"10.1016\/j.patcog.2026.113510_bib0014","doi-asserted-by":"crossref","DOI":"10.1016\/j.cmpb.2023.107937","article-title":"Spatio-temporal layers based intra-operative stereo depth estimation network via hierarchical prediction and progressive training","volume":"244","author":"Chen","year":"2024","journal-title":"Comput. Methods Programs Biomed."},{"key":"10.1016\/j.patcog.2026.113510_bib0015","series-title":"International Conference on Medical Image Computing and Computer-Assisted Intervention","first-page":"596","article-title":"StereoDiffusion: temporally consistent stereo depth estimation with diffusion models","author":"Xu","year":"2024"},{"key":"10.1016\/j.patcog.2026.113510_bib0016","doi-asserted-by":"crossref","DOI":"10.1016\/j.media.2022.102380","article-title":"StaSiS-Net: a stacked and siamese disparity estimation network for depth reconstruction in modern 3D laparoscopy","volume":"77","author":"Bardozzo","year":"2022","journal-title":"Med. Image Anal."},{"key":"10.1016\/j.patcog.2026.113510_bib0017","doi-asserted-by":"crossref","DOI":"10.1016\/j.compbiomed.2021.105109","article-title":"Unsupervised learning of depth estimation from imperfect rectified stereo laparoscopic images","volume":"140","author":"Luo","year":"2022","journal-title":"Comput. Biol. Med."},{"key":"10.1016\/j.patcog.2026.113510_bib0018","doi-asserted-by":"crossref","DOI":"10.1016\/j.compbiomed.2023.107121","article-title":"FRSR: framework for real-time scene reconstruction in robot-assisted minimally invasive surgery","volume":"163","author":"Chen","year":"2023","journal-title":"Comput. Biol. Med."},{"key":"10.1016\/j.patcog.2026.113510_bib0019","series-title":"MICCAI Workshop on Data Engineering in Medical Imaging","first-page":"43","article-title":"Exploring the effect of dataset diversity in self-supervised learning for surgical computer vision","author":"Jaspers","year":"2024"},{"key":"10.1016\/j.patcog.2026.113510_bib0020","series-title":"International Conference on Medical Image Computing and Computer-Assisted Intervention","first-page":"569","article-title":"Self-supervised learning for endoscopic video analysis","author":"Hirsch","year":"2023"},{"key":"10.1016\/j.patcog.2026.113510_bib0021","doi-asserted-by":"crossref","DOI":"10.1016\/j.compbiomed.2024.108546","article-title":"3D reconstruction from endoscopy images: a survey","volume":"175","author":"Yang","year":"2024","journal-title":"Comput. Biol. Med."},{"issue":"4","key":"10.1016\/j.patcog.2026.113510_bib0022","doi-asserted-by":"crossref","first-page":"1738","DOI":"10.1109\/TPAMI.2020.3032602","article-title":"A survey on deep learning techniques for stereo-based depth estimation","volume":"44","author":"Laga","year":"2020","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"issue":"6","key":"10.1016\/j.patcog.2026.113510_bib0023","doi-asserted-by":"crossref","first-page":"1203","DOI":"10.1007\/s11548-024-03137-8","article-title":"EndoSRR: a comprehensive multi-stage approach for endoscopic specular reflection removal","volume":"19","author":"Li","year":"2024","journal-title":"Int. J. Comput. Assist. Radiol. Surg."},{"key":"10.1016\/j.patcog.2026.113510_bib0024","series-title":"International Conference on Medical Image Computing and Computer-Assisted Intervention","first-page":"570","article-title":"CycleSTTN: a learning-based temporal model for specular augmentation in endoscopy","author":"Daher","year":"2023"},{"key":"10.1016\/j.patcog.2026.113510_bib0025","article-title":"Multi-frequency shared-feature-learning based diffusion model for removing surgical smoke","volume":"172","author":"Li","year":"2025","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.113510_bib0026","doi-asserted-by":"crossref","DOI":"10.1016\/j.media.2024.103131","article-title":"Tracking and mapping in medical computer vision: a review","volume":"94","author":"Schmidt","year":"2024","journal-title":"Med. Image Anal."},{"key":"10.1016\/j.patcog.2026.113510_bib0027","unstructured":"M. Allan, J. Mcleod, C. Wang, J.C. Rosenthal, Z. Hu, N. Gard, P. Eisert, K.X. Fu, T. Zeffiro, W. Xia, et al., Stereo correspondence and reconstruction of endoscopic data challenge, arXiv: 2101.01133(2021)."},{"key":"10.1016\/j.patcog.2026.113510_bib0028","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.patcog.2026.113510_bib0029","series-title":"International Conference on Medical Image Computing and Computer-Assisted Intervention","first-page":"604","article-title":"Stereo depth estimation via self-supervised contrastive representation learning","author":"Tukra","year":"2022"},{"key":"10.1016\/j.patcog.2026.113510_bib0030","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1109\/TIM.2024.3485441","article-title":"Real-time and high-accuracy switchable stereo depth estimation method utilizing self-supervised online learning mechanism for MIS","volume":"73","author":"Zheng","year":"2024","journal-title":"IEEE Trans. Instrum. Meas."},{"key":"10.1016\/j.patcog.2026.113510_bib0031","doi-asserted-by":"crossref","first-page":"4269","DOI":"10.1109\/TASE.2024.3409392","article-title":"Absolute monocular depth estimation on robotic visual and kinematics data via self-supervised learning","volume":"22","author":"Wei","year":"2024","journal-title":"IEEE Trans. Autom. Sci. Eng."},{"key":"10.1016\/j.patcog.2026.113510_bib0032","unstructured":"M. Ye, E. Johns, A. Handa, L. Zhang, P. Pratt, G.-Z. Yang, Self-supervised siamese learning on stereo image pairs for depth estimation in robotic surgery, arXiv: 1705.08260(2017)."},{"issue":"6","key":"10.1016\/j.patcog.2026.113510_bib0033","doi-asserted-by":"crossref","first-page":"516","DOI":"10.1109\/JPROC.2024.3435012","article-title":"When multitask learning meets partial supervision: a computer vision review","volume":"112","author":"Fontana","year":"2024","journal-title":"Proc. IEEE"},{"key":"10.1016\/j.patcog.2026.113510_bib0034","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."},{"issue":"11","key":"10.1016\/j.patcog.2026.113510_bib0035","doi-asserted-by":"crossref","first-page":"3218","DOI":"10.1109\/TMI.2022.3181229","article-title":"MSDESIS: multitask stereo disparity estimation and surgical instrument segmentation","volume":"41","author":"Psychogyios","year":"2022","journal-title":"IEEE Trans. Med. Imaging"},{"key":"10.1016\/j.patcog.2026.113510_bib0036","series-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","article-title":"Pyramid stereo matching network","author":"Chang","year":"2018"},{"key":"10.1016\/j.patcog.2026.113510_bib0037","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"5515","article-title":"Hierarchical deep stereo matching on high-resolution images","author":"Yang","year":"2019"},{"issue":"10","key":"10.1016\/j.patcog.2026.113510_bib0038","doi-asserted-by":"crossref","first-page":"2380","DOI":"10.1109\/TPAMI.2019.2942928","article-title":"Progressive fusion for unsupervised binocular depth estimation using cycled networks","volume":"42","author":"Pilzer","year":"2019","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.patcog.2026.113510_bib0039","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"7752","article-title":"A multi-task network for joint specular highlight detection and removal","author":"Fu","year":"2021"},{"issue":"2","key":"10.1016\/j.patcog.2026.113510_bib0040","doi-asserted-by":"crossref","first-page":"488","DOI":"10.1109\/TBME.2022.3195027","article-title":"Stereo dense scene reconstruction and accurate localization for learning-based navigation of laparoscope in minimally invasive surgery","volume":"70","author":"Wei","year":"2023","journal-title":"IEEE Trans. Biomed. Eng."},{"key":"10.1016\/j.patcog.2026.113510_bib0041","series-title":"International Conference on Pattern Recognition","first-page":"332","article-title":"Self-supervised siamese network using vision transformer for depth estimation in endoscopic surgeries","author":"Agarwal","year":"2025"},{"key":"10.1016\/j.patcog.2026.113510_bib0042","series-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","first-page":"8934","article-title":"PWC-Net: CNNs for optical flow using pyramid, warping, and cost volume","author":"Sun","year":"2018"},{"key":"10.1016\/j.patcog.2026.113510_bib0043","series-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","first-page":"4884","article-title":"Occlusion aware unsupervised learning of optical flow","author":"Wang","year":"2018"},{"key":"10.1016\/j.patcog.2026.113510_bib0044","series-title":"Computer Vision\u2013ECCV 2020: 16th European Conference, Glasgow, UK, August 23\u201328, 2020, Proceedings, Part II 16","first-page":"402","article-title":"RAFT: recurrent all-pairs field transforms for optical flow","author":"Teed","year":"2020"},{"key":"10.1016\/j.patcog.2026.113510_bib0045","series-title":"Medical Image Understanding and Analysis: 25th Annual Conference","first-page":"337","article-title":"Dense depth estimation from stereo endoscopy videos using unsupervised optical flow methods","author":"Yang","year":"2021"},{"issue":"12","key":"10.1016\/j.patcog.2026.113510_bib0046","doi-asserted-by":"crossref","first-page":"4356","DOI":"10.1109\/TMI.2024.3439701","article-title":"Self-supervised cyclic diffeomorphic mapping for soft tissue deformation recovery in robotic surgery scenes","volume":"43","author":"Gong","year":"2024","journal-title":"IEEE Trans. Med. Imaging"},{"key":"10.1016\/j.patcog.2026.113510_bib0047","series-title":"International Conference on Medical Image Computing and Computer-Assisted Intervention","first-page":"350","article-title":"Free-surgs: SFM-free 3D Gaussian splatting for surgical scene reconstruction","author":"Guo","year":"2024"}],"container-title":["Pattern Recognition"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0031320326004760?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0031320326004760?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,6,3]],"date-time":"2026-06-03T13:08:41Z","timestamp":1780492121000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0031320326004760"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,11]]},"references-count":47,"alternative-id":["S0031320326004760"],"URL":"https:\/\/doi.org\/10.1016\/j.patcog.2026.113510","relation":{},"ISSN":["0031-3203"],"issn-type":[{"value":"0031-3203","type":"print"}],"subject":[],"published":{"date-parts":[[2026,11]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Simultaneous surgical stereo depth and motion estimation via brightness-aware self-supervised learning","name":"articletitle","label":"Article Title"},{"value":"Pattern Recognition","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.patcog.2026.113510","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":"113510"}}