{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,24]],"date-time":"2026-03-24T17:55:34Z","timestamp":1774374934717,"version":"3.50.1"},"publisher-location":"Cham","reference-count":38,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031198236","type":"print"},{"value":"9783031198243","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\/978-3-031-19824-3_16","type":"book-chapter","created":{"date-parts":[[2022,11,10]],"date-time":"2022-11-10T21:14:32Z","timestamp":1668114872000},"page":"263-279","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":35,"title":["Context-Enhanced Stereo Transformer"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5449-9490","authenticated-orcid":false,"given":"Weiyu","family":"Guo","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5874-4713","authenticated-orcid":false,"given":"Zhaoshuo","family":"Li","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1159-3115","authenticated-orcid":false,"given":"Yongkui","family":"Yang","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2855-9570","authenticated-orcid":false,"given":"Zheng","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Russell H.","family":"Taylor","sequence":"additional","affiliation":[]},{"given":"Mathias","family":"Unberath","sequence":"additional","affiliation":[]},{"given":"Alan","family":"Yuille","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0711-7004","authenticated-orcid":false,"given":"Yingwei","family":"Li","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2022,11,11]]},"reference":[{"key":"16_CR1","doi-asserted-by":"publisher","unstructured":"Butler, D.J., Wulff, J., Stanley, G.B., Black, M.J.: A naturalistic open source movie for optical flow evaluation. In: Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C. (eds.) ECCV 2012. LNCS, vol. 7577, pp. 611\u2013625. Springer, Heidelberg (2012). https:\/\/doi.org\/10.1007\/978-3-642-33783-3_44","DOI":"10.1007\/978-3-642-33783-3_44"},{"key":"16_CR2","doi-asserted-by":"crossref","unstructured":"Chang, J.R., Chen, Y.S.: Pyramid stereo matching network. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5410\u20135418 (2018)","DOI":"10.1109\/CVPR.2018.00567"},{"issue":"5","key":"16_CR3","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3465055","volume":"12","author":"S Chaudhari","year":"2021","unstructured":"Chaudhari, S., Mithal, V., Polatkan, G., Ramanath, R.: An attentive survey of attention models. ACM Trans. Intell. Syst. Technol. 12(5), 1\u201332 (2021)","journal-title":"ACM Trans. Intell. Syst. Technol."},{"key":"16_CR4","doi-asserted-by":"crossref","unstructured":"Chen, Z., Sun, X., Wang, L., Yu, Y., Huang, C.: A deep visual correspondence embedding model for stereo matching costs. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 972\u2013980 (2015)","DOI":"10.1109\/ICCV.2015.117"},{"key":"16_CR5","unstructured":"Cuturi, M.: Sinkhorn distances: lightspeed computation of optimal transport. Adv, Neural Inform. Process. Syst. 26 (2013)"},{"key":"16_CR6","doi-asserted-by":"crossref","unstructured":"Girshick, R.: Fast R-CNN. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1440\u20131448 (2015)","DOI":"10.1109\/ICCV.2015.169"},{"key":"16_CR7","unstructured":"Guo, M.H., et al.: Attention mechanisms in computer vision: a survey. arXiv preprint arXiv:2111.07624 (2021)"},{"key":"16_CR8","doi-asserted-by":"crossref","unstructured":"Guo, X., Yang, K., Yang, W., Wang, X., Li, H.: Group-wise correlation stereo network. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 3273\u20133282 (2019)","DOI":"10.1109\/CVPR.2019.00339"},{"key":"16_CR9","doi-asserted-by":"crossref","unstructured":"Hartmann, W., Galliani, S., Havlena, M., Gool, L.V., Schindler, K.: Learned multi-patch similarity. In: 2017 IEEE International Conference on Computer Vision (ICCV) (2017)","DOI":"10.1109\/ICCV.2017.176"},{"key":"16_CR10","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. IEEE (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"16_CR11","unstructured":"He, P., Liu, X., Gao, J., Chen, W.: Deberta: decoding-enhanced bert with disentangled attention. arXiv (2020)"},{"issue":"2","key":"16_CR12","doi-asserted-by":"publisher","first-page":"328","DOI":"10.1109\/TPAMI.2007.1166","volume":"30","author":"H Hirschmuller","year":"2007","unstructured":"Hirschmuller, H.: Stereo processing by semiglobal matching and mutual information. IEEE Trans. Patt. Anal. Mach. Intell. 30(2), 328\u2013341 (2007)","journal-title":"IEEE Trans. Patt. Anal. Mach. Intell."},{"key":"16_CR13","doi-asserted-by":"crossref","unstructured":"Huang, G., Liu, Z., Laurens, V., Weinberger, K.Q.: Densely connected convolutional networks. IEEE Computer Society (2016)","DOI":"10.1109\/CVPR.2017.243"},{"key":"16_CR14","doi-asserted-by":"crossref","unstructured":"Huang, P.H., Matzen, K., Kopf, J., Ahuja, N., Huang, J.B.: Deepmvs: learning multi-view stereopsis. IEEE (2018)","DOI":"10.1109\/CVPR.2018.00298"},{"key":"16_CR15","doi-asserted-by":"crossref","unstructured":"Laga, H., Jospin, L.V., Boussaid, F., Bennamoun, M.: A survey on deep learning techniques for stereo-based depth estimation. IEEE Trans. Patt. Anal. Mach. Intell. 44, 1738\u20131764 (2020)","DOI":"10.1109\/TPAMI.2020.3032602"},{"key":"16_CR16","unstructured":"Li, Z., Drenkow, N., et al.: On the sins of image synthesis loss for self-supervised depth estimation. arXiv preprint arXiv:2109.06163 (2021)"},{"key":"16_CR17","doi-asserted-by":"crossref","unstructured":"Li, Z., et al.: Revisiting stereo depth estimation from a sequence-to-sequence perspective with transformers. In: 2021 IEEE International Conference on Computer Vision (ICCV) (2021)","DOI":"10.1109\/ICCV48922.2021.00614"},{"key":"16_CR18","unstructured":"Li, Z., et al.: Temporally consistent online depth estimation in dynamic scenes. arXiv preprint arXiv:2111.09337 (2021)"},{"key":"16_CR19","doi-asserted-by":"crossref","unstructured":"Lipson, L., Teed, Z., Deng, J.: Raft-stereo: multilevel recurrent field transforms for stereo matching. In: 2021 International Conference on 3D Vision (3DV), pp. 218\u2013227. IEEE (2021)","DOI":"10.1109\/3DV53792.2021.00032"},{"key":"16_CR20","doi-asserted-by":"crossref","unstructured":"Liu, X., et al.: Extremely dense point correspondences using a learned feature descriptor. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4847\u20134856 (2020)","DOI":"10.1109\/CVPR42600.2020.00490"},{"key":"16_CR21","doi-asserted-by":"crossref","unstructured":"Liu, Y., Zhu, L., Yamada, M., Yang, Y.: Semantic correspondence as an optimal transport problem. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4463\u20134472 (2020)","DOI":"10.1109\/CVPR42600.2020.00452"},{"key":"16_CR22","unstructured":"Loshchilov, I., Hutter, F.: Decoupled weight decay regularization. arXiv preprint arXiv:1711.05101 (2017)"},{"key":"16_CR23","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: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4040\u20134048 (2016)","DOI":"10.1109\/CVPR.2016.438"},{"key":"16_CR24","doi-asserted-by":"crossref","unstructured":"Menze, M., Geiger, A.: Object scene flow for autonomous vehicles. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3061\u20133070 (2015)","DOI":"10.1109\/CVPR.2015.7298925"},{"key":"16_CR25","unstructured":"Paszke, A., et al.: Pytorch: An imperative style, high-performance deep learning library. Adv. Neural Inf. Process. Syst. 32 (2019)"},{"key":"16_CR26","doi-asserted-by":"publisher","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","DOI":"10.1007\/978-3-319-11752-2_3"},{"key":"16_CR27","doi-asserted-by":"crossref","unstructured":"Schmid, K., Tomic, T., Ruess, F., Hirschm\u00fcller, H., Suppa, M.: Stereo vision based indoor\/outdoor navigation for flying robots. In: 2013 IEEE\/RSJ International Conference on Intelligent Robots and Systems, pp. 3955\u20133962. IEEE (2013)","DOI":"10.1109\/IROS.2013.6696922"},{"key":"16_CR28","doi-asserted-by":"crossref","unstructured":"Sun, J., et al.: DISP R-CNN: Stereo 3d object detection via shape prior guided instance disparity estimation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10548\u201310557 (2020)","DOI":"10.1109\/CVPR42600.2020.01056"},{"key":"16_CR29","doi-asserted-by":"crossref","unstructured":"Tomono, M.: Robust 3d slam with a stereo camera based on an edge-point ICP algorithm. In: 2009 IEEE International Conference on Robotics and Automation, pp. 4306\u20134311. IEEE (2009)","DOI":"10.1109\/ROBOT.2009.5152529"},{"key":"16_CR30","unstructured":"Vaswani, A., et al.: Attention is all you need. Adv. Neural Inf. Process. Syst. 30 (2017)"},{"key":"16_CR31","doi-asserted-by":"publisher","unstructured":"Wang, H., Zhu, Y., Green, B., Adam, H., Yuille, A., Chen, L.C.: Axial-DeepLab: stand-Alone Axial-Attention for Panoptic Segmentation. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12349, pp. 108\u2013126. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58548-8_7","DOI":"10.1007\/978-3-030-58548-8_7"},{"key":"16_CR32","doi-asserted-by":"crossref","unstructured":"Xu, H., Zhang, J.: Aanet: adaptive aggregation network for efficient stereo matching. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 1959\u20131968 (2020)","DOI":"10.1109\/CVPR42600.2020.00203"},{"key":"16_CR33","unstructured":"Yang, J., et al.: Focal self-attention for local-global interactions in vision transformers. arXiv preprint arXiv:2107.00641 (2021)"},{"key":"16_CR34","doi-asserted-by":"crossref","unstructured":"Yao, C., Jia, Y., Di, H., Li, P., Wu, Y.: A decomposition model for stereo matching. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 6091\u20136100 (2021)","DOI":"10.1109\/CVPR46437.2021.00603"},{"key":"16_CR35","doi-asserted-by":"crossref","unstructured":"Zendel, O., Murschitz, M., Humenberger, M., Herzner, W.: Cv-hazop: introducing test data validation for computer vision. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2066\u20132074 (2015)","DOI":"10.1109\/ICCV.2015.239"},{"key":"16_CR36","doi-asserted-by":"crossref","unstructured":"Zhang, F., Prisacariu, V., Yang, R., Torr, P.H.: Ga-net: guided aggregation net for end-to-end stereo matching. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 185\u2013194 (2019)","DOI":"10.1109\/CVPR.2019.00027"},{"key":"16_CR37","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Qiu, W., Chen, Q., Hu, X., Yuille, A.: Unrealstereo: controlling hazardous factors to analyze stereo vision. In: 2018 International Conference on 3D Vision (3DV), pp. 228\u2013237. IEEE (2018)","DOI":"10.1109\/3DV.2018.00035"},{"issue":"9","key":"16_CR38","doi-asserted-by":"publisher","first-page":"1612","DOI":"10.1007\/s11431-020-1582-8","volume":"63","author":"C Zhao","year":"2020","unstructured":"Zhao, C., Sun, Q., Zhang, C., Tang, Y., Qian, F.: Monocular depth estimation based on deep learning: an overview. Sci. China Technol. Sci. 63(9), 1612\u20131627 (2020)","journal-title":"Sci. China Technol. Sci."}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2022"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-19824-3_16","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,11,12]],"date-time":"2022-11-12T00:09:49Z","timestamp":1668211789000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-19824-3_16"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031198236","9783031198243"],"references-count":38,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-19824-3_16","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":"11 November 2022","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":"Tel Aviv","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Israel","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":"23 October 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27 October 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2022.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","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":"CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"5804","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":"1645","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":"28% - 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":"3.21","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":"3.91","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)"}}]}}