{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,25]],"date-time":"2026-09-25T11:30:39Z","timestamp":1790335839592,"version":"4.1.0"},"publisher-location":"Cham","reference-count":37,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031164484","type":"print"},{"value":"9783031164491","type":"electronic"}],"license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022]]},"DOI":"10.1007\/978-3-031-16449-1_44","type":"book-chapter","created":{"date-parts":[[2022,9,16]],"date-time":"2022-09-16T08:04:54Z","timestamp":1663315494000},"page":"464-474","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":15,"title":["Deep Laparoscopic Stereo Matching with\u00a0Transformers"],"prefix":"10.1007","author":[{"given":"Xuelian","family":"Cheng","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yiran","family":"Zhong","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mehrtash","family":"Harandi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tom","family":"Drummond","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhiyong","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zongyuan","family":"Ge","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2022,9,17]]},"reference":[{"key":"44_CR1","unstructured":"Allan, M., et al.: Stereo correspondence and reconstruction of endoscopic data challenge. arXiv preprint arXiv:2101.01133 (2021)"},{"key":"44_CR2","doi-asserted-by":"crossref","unstructured":"Cartucho, J., Tukra, S., Li, Y., S. Elson, D., Giannarou, S.: Visionblender: a tool to efficiently generate computer vision datasets for robotic surgery. CMBBE Imaging Vis. 9(4), 331\u2013338 (2021)","DOI":"10.1080\/21681163.2020.1835546"},{"issue":"12","key":"44_CR3","doi-asserted-by":"publisher","DOI":"10.1088\/1742-5468\/ab39d9","volume":"2019","author":"P Chaudhari","year":"2019","unstructured":"Chaudhari, P., et al.: Entropy-SGD: biasing gradient descent into wide valleys. J. Stat. Mech. Theory Exp. 2019(12), 124018 (2019)","journal-title":"J. Stat. Mech. Theory Exp."},{"key":"44_CR4","doi-asserted-by":"crossref","unstructured":"Cheng, X., Zhong, Y., Dai, Y., Ji, P., Li, H.: Noise-aware unsupervised deep lidar-stereo fusion. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00650"},{"key":"44_CR5","unstructured":"Cheng, X., et al.: Hierarchical neural architecture search for deep stereo matching. In: NeurIPS, vol. 33 (2020)"},{"key":"44_CR6","series-title":"Lecture Notes in Electrical Engineering","doi-asserted-by":"publisher","first-page":"59","DOI":"10.1007\/978-981-16-3880-0_7","volume-title":"Proceedings of 2021 International Conference on Medical Imaging and Computer-Aided Diagnosis (MICAD 2021)","author":"N Chong","year":"2022","unstructured":"Chong, N., et al.: Virtual reality application for laparoscope in clinical surgery based on siamese network and census transformation. In: Su, R., Zhang, Y.-D., Liu, H. (eds.) MICAD 2021. LNEE, vol. 784, pp. 59\u201370. Springer, Singapore (2022). https:\/\/doi.org\/10.1007\/978-981-16-3880-0_7"},{"key":"44_CR7","unstructured":"Dosovitskiy, A., et al.: An image is worth 16x16 words: transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)"},{"key":"44_CR8","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"25","DOI":"10.1007\/978-3-642-19315-6_3","volume-title":"Computer Vision \u2013 ACCV 2010","author":"A Geiger","year":"2011","unstructured":"Geiger, A., Roser, M., Urtasun, R.: Efficient large-scale stereo matching. In: Kimmel, R., Klette, R., Sugimoto, A. (eds.) ACCV 2010. LNCS, vol. 6492, pp. 25\u201338. Springer, Heidelberg (2011). https:\/\/doi.org\/10.1007\/978-3-642-19315-6_3"},{"key":"44_CR9","doi-asserted-by":"crossref","unstructured":"Hore, A., Ziou, D.: Image quality metrics: Psnr vs. ssim. In: 2010 20th International Conference on Pattern Recognition, pp. 2366\u20132369. IEEE (2010)","DOI":"10.1109\/ICPR.2010.579"},{"key":"44_CR10","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"227","DOI":"10.1007\/978-3-030-87202-1_22","volume-title":"Medical Image Computing and Computer Assisted Intervention \u2013 MICCAI 2021","author":"B Huang","year":"2021","unstructured":"Huang, B., et al.: Self-supervised generative adversarial network for depth estimation in\u00a0laparoscopic images. In: de Bruijne, M., et al. (eds.) MICCAI 2021. LNCS, vol. 12904, pp. 227\u2013237. Springer, Cham (2021). https:\/\/doi.org\/10.1007\/978-3-030-87202-1_22"},{"key":"44_CR11","unstructured":"Keskar, N.S., Mudigere, D., Nocedal, J., Smelyanskiy, M., Tang, P.T.P.: On large-batch training for deep learning: Generalization gap and sharp minima. ICLR (2017)"},{"key":"44_CR12","unstructured":"Li, H., Xu, Z., Taylor, G., Studer, C., Goldstein, T.: Visualizing the loss landscape of neural nets. NeurIPS 31 (2018)"},{"key":"44_CR13","doi-asserted-by":"crossref","unstructured":"Li, Z., et al.: Revisiting stereo depth estimation from a sequence-to-sequence perspective with transformers. In: ICCV, pp. 6197\u20136206, October 2021","DOI":"10.1109\/ICCV48922.2021.00614"},{"key":"44_CR14","doi-asserted-by":"crossref","unstructured":"Lipson, L., Teed, Z., Deng, J.: RAFT-Stereo: Multilevel Recurrent Field Transforms for Stereo Matching. arXiv preprint arXiv:2109.07547 (2021)","DOI":"10.1109\/3DV53792.2021.00032"},{"key":"44_CR15","doi-asserted-by":"crossref","unstructured":"Liu, Z., et al.: Swin transformer: Hierarchical vision transformer using shifted windows. In: ICCV, pp. 10012\u201310022 (2021)","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"44_CR16","unstructured":"Liu, Z., et al.: Video swin transformer. arXiv preprint arXiv:2106.13230 (2021)"},{"key":"44_CR17","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"415","DOI":"10.1007\/978-3-030-87202-1_40","volume-title":"Medical Image Computing and Computer Assisted Intervention \u2013 MICCAI 2021","author":"Y Long","year":"2021","unstructured":"Long, Y., et al.: E-DSSR: efficient dynamic surgical scene reconstruction with\u00a0transformer-based stereoscopic depth perception. In: de Bruijne, M., et al. (eds.) MICCAI 2021. LNCS, vol. 12904, pp. 415\u2013425. Springer, Cham (2021). https:\/\/doi.org\/10.1007\/978-3-030-87202-1_40"},{"key":"44_CR18","doi-asserted-by":"crossref","unstructured":"Mayer, N., et al.: A large dataset to train convolutional networks for disparity, optical flow, and scene flow estimation. In: CVPR, pp. 4040\u20134048 (2016)","DOI":"10.1109\/CVPR.2016.438"},{"key":"44_CR19","doi-asserted-by":"crossref","unstructured":"Menze, M., Geiger, A.: Object scene flow for autonomous vehicles. In: CVPR (2015)","DOI":"10.1109\/CVPR.2015.7298925"},{"issue":"3","key":"44_CR20","doi-asserted-by":"publisher","first-page":"189","DOI":"10.1016\/j.suronc.2011.07.002","volume":"20","author":"S Nicolau","year":"2011","unstructured":"Nicolau, S., Soler, L., Mutter, D., Marescaux, J.: Augmented reality in laparoscopic surgical oncology. Surg. Oncol. 20(3), 189\u2013201 (2011)","journal-title":"Surg. Oncol."},{"issue":"3S","key":"44_CR21","doi-asserted-by":"publisher","first-page":"S86","DOI":"10.1093\/neuros\/nyw077","volume":"80","author":"SC Overley","year":"2017","unstructured":"Overley, S.C., Cho, S.K., Mehta, A.I., Arnold, P.M.: Navigation and robotics in spinal surgery: where are we now? Neurosurgery 80(3S), S86\u2013S99 (2017)","journal-title":"Neurosurgery"},{"key":"44_CR22","unstructured":"Qin, Z., et al.: Cosformer: Rethinking softmax in attention. In: ICLR (2022)"},{"key":"44_CR23","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"31","DOI":"10.1007\/978-3-319-11752-2_3","volume-title":"Pattern Recognition","author":"D Scharstein","year":"2014","unstructured":"Scharstein, D., et al.: High-resolution stereo datasets with subpixel-accurate ground truth. In: Jiang, X., Hornegger, J., Koch, R. (eds.) GCPR 2014. LNCS, vol. 8753, pp. 31\u201342. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-11752-2_3"},{"issue":"5","key":"44_CR24","doi-asserted-by":"publisher","first-page":"1299","DOI":"10.1162\/089976698300017467","volume":"10","author":"B Sch\u00f6lkopf","year":"1998","unstructured":"Sch\u00f6lkopf, B., Smola, A., M\u00fcller, K.R.: Nonlinear component analysis as a kernel eigenvalue problem. Neural Comput. 10(5), 1299\u20131319 (1998)","journal-title":"Neural Comput."},{"key":"44_CR25","unstructured":"Sun, W., Qin, Z., Deng, H., Wang, J., Zhang, Y., Zhang, K., Barnes, N., Birchfield, S., Kong, L., Zhong, Y.: Vicinity vision transformer. In: arxiv. p. 2206.10552 (2022)"},{"key":"44_CR26","doi-asserted-by":"crossref","unstructured":"Wang, J., et al.: Deep two-view structure-from-motion revisited. In: CVPR, pp. 8953\u20138962, June 2021","DOI":"10.1109\/CVPR46437.2021.00884"},{"key":"44_CR27","unstructured":"Wang, J., Zhong, Y., Dai, Y., Zhang, K., Ji, P., Li, H.: Displacement-invariant matching cost learning for accurate optical flow estimation. In: NeurIPS (2020)"},{"key":"44_CR28","doi-asserted-by":"crossref","unstructured":"Wang, W., et al.: Pyramid vision transformer: a versatile backbone for dense prediction without convolutions. In: ICCV, pp. 568\u2013578 (2021)","DOI":"10.1109\/ICCV48922.2021.00061"},{"issue":"4","key":"44_CR29","first-page":"600","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. TIP 13(4), 600\u2013612 (2004)","journal-title":"TIP"},{"key":"44_CR30","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"756","DOI":"10.1007\/978-3-319-10602-1_49","volume-title":"Computer Vision \u2013 ECCV 2014","author":"K Yamaguchi","year":"2014","unstructured":"Yamaguchi, K., McAllester, D., Urtasun, R.: Efficient joint segmentation, occlusion labeling, stereo and flow estimation. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8693, pp. 756\u2013771. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10602-1_49"},{"key":"44_CR31","doi-asserted-by":"crossref","unstructured":"Ye, M., Johns, E., Handa, A., Zhang, L., Pratt, P., Yang, G.Z.: Self-supervised siamese learning on stereo image pairs for depth estimation in robotic surgery. arXiv preprint arXiv:1705.08260 (2017)","DOI":"10.31256\/HSMR2017.14"},{"key":"44_CR32","unstructured":"Zhong, Y., Dai, Y., Li, H.: Self-supervised learning for stereo matching with self-improving ability (2017)"},{"key":"44_CR33","doi-asserted-by":"crossref","unstructured":"Zhong, Y., Dai, Y., Li, H.: 3d geometry-aware semantic labeling of outdoor street scenes. In: ICPR (2018)","DOI":"10.1109\/ICPR.2018.8545378"},{"key":"44_CR34","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"441","DOI":"10.1007\/978-3-030-01240-3_27","volume-title":"Computer Vision \u2013 ECCV 2018","author":"Y Zhong","year":"2018","unstructured":"Zhong, Y., Dai, Y., Li, H.: Stereo computation for a single mixture image. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11213, pp. 441\u2013456. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01240-3_27"},{"key":"44_CR35","doi-asserted-by":"crossref","unstructured":"Zhong, Y., Ji, P., Wang, J., Dai, Y., Li, H.: Unsupervised deep epipolar flow for stationary or dynamic scenes. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.01237"},{"key":"44_CR36","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"104","DOI":"10.1007\/978-3-030-01216-8_7","volume-title":"Computer Vision \u2013 ECCV 2018","author":"Y Zhong","year":"2018","unstructured":"Zhong, Y., Li, H., Dai, Y.: Open-world stereo video matching with deep RNN. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11206, pp. 104\u2013119. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01216-8_7"},{"key":"44_CR37","doi-asserted-by":"crossref","unstructured":"Zhong, Y., et al.: Displacement-invariant cost computation for stereo matching. In: IJCV, March 2022","DOI":"10.1007\/s11263-022-01595-8"}],"container-title":["Lecture Notes in Computer Science","Medical Image Computing and Computer Assisted Intervention \u2013 MICCAI 2022"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-16449-1_44","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,7]],"date-time":"2024-03-07T16:58:11Z","timestamp":1709830691000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-16449-1_44"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031164484","9783031164491"],"references-count":37,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-16449-1_44","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022]]},"assertion":[{"value":"17 September 2022","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"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":"Singapore","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Singapore","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2022","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18 September 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22 September 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"25","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"miccai2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Microsoft Conference","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"1831","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"574","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"31% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"5","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}