{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,10]],"date-time":"2026-07-10T15:34:45Z","timestamp":1783697685705,"version":"3.55.0"},"publisher-location":"Cham","reference-count":35,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030695248","type":"print"},{"value":"9783030695255","type":"electronic"}],"license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021]]},"DOI":"10.1007\/978-3-030-69525-5_7","type":"book-chapter","created":{"date-parts":[[2021,2,26]],"date-time":"2021-02-26T16:21:16Z","timestamp":1614356476000},"page":"106-122","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":17,"title":["SGNet: Semantics Guided Deep Stereo Matching"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4114-9066","authenticated-orcid":false,"given":"Shuya","family":"Chen","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3329-7037","authenticated-orcid":false,"given":"Zhiyu","family":"Xiang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2413-6837","authenticated-orcid":false,"given":"Chengyu","family":"Qiao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6809-4291","authenticated-orcid":false,"given":"Yiman","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1516-1558","authenticated-orcid":false,"given":"Tingming","family":"Bai","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2021,2,27]]},"reference":[{"key":"7_CR1","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: Proceedings of the IEEE\/RSJ International Conference on Intelligent Robots and Systems, pp. 3955\u20133962. IEEE (2013)","DOI":"10.1109\/IROS.2013.6696922"},{"key":"7_CR2","doi-asserted-by":"crossref","unstructured":"Chen, C., Seff, A., Kornhauser, A., Xiao, J.: DeepDriving: learning affordance for direct perception in autonomous driving. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2722\u20132730. IEEE (2015)","DOI":"10.1109\/ICCV.2015.312"},{"key":"7_CR3","first-page":"2287","volume":"17","author":"J \u017dbontar","year":"2016","unstructured":"\u017dbontar, J., LeCun, Y.: Stereo matching by training a convolutional neural network to compare image patches. J. Mach. Learn. Res. 17, 2287\u20132318 (2016)","journal-title":"J. Mach. Learn. Res."},{"key":"7_CR4","doi-asserted-by":"crossref","unstructured":"Shaked, A., Wolf, L.: Improved stereo matching with constant highway networks and reflective confidence learning. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4641\u20134650. IEEE (2017)","DOI":"10.1109\/CVPR.2017.730"},{"key":"7_CR5","doi-asserted-by":"crossref","unstructured":"Long, J., Shelhamer, E., Darrell, T.: Fully convolutional networks for semantic segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3431\u20133440. IEEE (2015)","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"7_CR6","doi-asserted-by":"crossref","unstructured":"Zhao, H., Shi, J., Qi, X., Wang, X., Jia, J.: Pyramid scene parsing network. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2881\u20132890. IEEE (2017)","DOI":"10.1109\/CVPR.2017.660"},{"key":"7_CR7","doi-asserted-by":"crossref","unstructured":"Cheng, J., Tsai, Y.H., Wang, S., Yang, M.H.: SegFlow: joint learning for video object segmentation and optical flow. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 686\u2013695. IEEE (2017)","DOI":"10.1109\/ICCV.2017.81"},{"key":"7_CR8","doi-asserted-by":"crossref","unstructured":"Zhang, Z., Cui, Z., Xu, C., Jie, Z., Li, X., Yang, J.: Joint task-recursive learning for semantic segmentation and depth estimation. In: Proceedings of the European Conference on Computer Vision, pp. 235\u2013251 (2018)","DOI":"10.1007\/978-3-030-01249-6_15"},{"key":"7_CR9","doi-asserted-by":"crossref","unstructured":"Jiao, J., Cao, Y., Song, Y., Lau, R.: Look deeper into depth: monocular depth estimation with semantic booster and attention-driven loss. In: Proceedings of the European Conference on Computer Vision, pp. 53\u201369 (2018)","DOI":"10.1007\/978-3-030-01267-0_4"},{"key":"7_CR10","doi-asserted-by":"crossref","unstructured":"Chen, P.Y., Liu, A.H., Liu, Y.C., Wang, Y.C.F.: Towards scene understanding: unsupervised monocular depth estimation with semantic-aware representation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2624\u20132632. IEEE (2019)","DOI":"10.1109\/CVPR.2019.00273"},{"key":"7_CR11","doi-asserted-by":"publisher","first-page":"635","DOI":"10.3390\/s20030635","volume":"20","author":"N Zou","year":"2020","unstructured":"Zou, N., Xiang, Z., Chen, Y., Chen, S., Qiao, C.: Simultaneous semantic segmentation and depth completion with constraint of boundary. Sensors 20, 635 (2020)","journal-title":"Sensors"},{"key":"7_CR12","doi-asserted-by":"crossref","unstructured":"Yang, G., Zhao, H., Shi, J., Deng, Z., Jia, J.: SegStereo: exploiting semantic information for disparity estimation. In: Proceedings of the European Conference on Computer Vision, pp. 636\u2013651 (2018)","DOI":"10.1007\/978-3-030-01234-2_39"},{"key":"7_CR13","doi-asserted-by":"publisher","first-page":"1162","DOI":"10.1109\/LRA.2019.2894913","volume":"4","author":"J Zhang","year":"2019","unstructured":"Zhang, J., Skinner, K.A., Vasudevan, R., Johnson-Roberson, M.: DispSegNet: leveraging semantics for end-to-end learning of disparity estimation from stereo imagery. IEEE Robot. Autom. Lett. 4, 1162\u20131169 (2019)","journal-title":"IEEE Robot. Autom. Lett."},{"key":"7_CR14","doi-asserted-by":"crossref","unstructured":"Wu, Z., Wu, X., Zhang, X., Wang, S., Ju, L.: Semantic stereo matching with pyramid cost volumes. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 7484\u20137493. IEEE (2019)","DOI":"10.1109\/ICCV.2019.00758"},{"key":"7_CR15","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. IEEE (2018)","DOI":"10.1109\/CVPR.2018.00567"},{"key":"7_CR16","doi-asserted-by":"publisher","first-page":"7","DOI":"10.1023\/A:1014573219977","volume":"47","author":"D Scharstein","year":"2001","unstructured":"Scharstein, D., Szeliski, R., Zabih, R.: A taxonomy and evaluation of dense two-frame stereo correspondence algorithms. Int. J. Comput. Vis. 47, 7\u201342 (2001). https:\/\/doi.org\/10.1023\/A:1014573219977","journal-title":"Int. J. Comput. Vis."},{"key":"7_CR17","doi-asserted-by":"crossref","unstructured":"Kanade, T., Kano, H., Kimura, S., Yoshida, A., Oda, K.: Development of a video-rate stereo machine. In: Proceedings of the 1995 IEEE\/RSJ International Conference on Intelligent Robots and Systems. Human Robot Interaction and Cooperative Robots, vol. 3, pp. 95\u2013100. IEEE (1995)","DOI":"10.1109\/IROS.1995.525868"},{"key":"7_CR18","doi-asserted-by":"publisher","first-page":"1222","DOI":"10.1109\/34.969114","volume":"23","author":"Y Boykov","year":"2001","unstructured":"Boykov, Y., Veksler, O., Zabih, R.: Fast approximate energy minimization via graph cuts. IEEE Trans. Pattern Anal. Mach. Intell. 23, 1222\u20131239 (2001)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"7_CR19","doi-asserted-by":"crossref","unstructured":"Klaus, A., Sormann, M., Karner, K.: Segment-based stereo matching using belief propagation and a self-adapting dissimilarity measure. In: 18th International Conference on Pattern Recognition (ICPR 2006), vol. 3, pp. 15\u201318. IEEE (2006)","DOI":"10.1109\/ICPR.2006.1033"},{"key":"7_CR20","doi-asserted-by":"crossref","unstructured":"Dosovitskiy, A., et al.: FlowNet: learning optical flow with convolutional networks. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2758\u20132766. IEEE (2015)","DOI":"10.1109\/ICCV.2015.316"},{"key":"7_CR21","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. IEEE (2016)","DOI":"10.1109\/CVPR.2016.438"},{"key":"7_CR22","doi-asserted-by":"crossref","unstructured":"Pang, J., Sun, W., Ren, J.S., Yang, C., Yan, Q.: Cascade residual learning: a two-stage convolutional neural network for stereo matching. In: Proceedings of the IEEE International Conference on Computer Vision Workshops, pp. 887\u2013895. IEEE (2017)","DOI":"10.1109\/ICCVW.2017.108"},{"key":"7_CR23","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. IEEE (2020)","DOI":"10.1109\/CVPR42600.2020.00203"},{"key":"7_CR24","doi-asserted-by":"crossref","unstructured":"Kendall, A., et al.: End-to-end learning of geometry and context for deep stereo regression. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 66\u201375. IEEE (2017)","DOI":"10.1109\/ICCV.2017.17"},{"key":"7_CR25","doi-asserted-by":"crossref","unstructured":"Yu, L., Wang, Y., Wu, Y., Jia, Y.: Deep stereo matching with explicit cost aggregation sub-architecture. In: Thirty-Second AAAI Conference on Artificial Intelligence (2018)","DOI":"10.1609\/aaai.v32i1.12267"},{"key":"7_CR26","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"20","DOI":"10.1007\/978-3-030-20873-8_2","volume-title":"Computer Vision \u2013 ACCV 2018","author":"X Song","year":"2019","unstructured":"Song, X., Zhao, X., Hu, H., Fang, L.: EdgeStereo: a context integrated residual pyramid network for stereo matching. In: Jawahar, C.V., Li, H., Mori, G., Schindler, K. (eds.) ACCV 2018. LNCS, vol. 11365, pp. 20\u201335. Springer, Cham (2019). https:\/\/doi.org\/10.1007\/978-3-030-20873-8_2"},{"key":"7_CR27","doi-asserted-by":"publisher","first-page":"910","DOI":"10.1007\/s11263-019-01287-w","volume":"128","author":"X Song","year":"2020","unstructured":"Song, X., Zhao, X., Fang, L., Hu, H., Yu, Y.: EdgeStereo: an effective multi-task learning network for stereo matching and edge detection. Int. J. Comput. Vis. 128, 910\u2013930 (2020). https:\/\/doi.org\/10.1007\/s11263-019-01287-w","journal-title":"Int. J. Comput. Vis."},{"key":"7_CR28","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 Conference on Computer Vision and Pattern Recognition, pp. 185\u2013194. IEEE (2019)","DOI":"10.1109\/CVPR.2019.00027"},{"key":"7_CR29","doi-asserted-by":"publisher","first-page":"328","DOI":"10.1109\/TPAMI.2007.1166","volume":"30","author":"H Hirschmuller","year":"2008","unstructured":"Hirschmuller, H.: Stereo processing by semiglobal matching and mutual information. IEEE Trans. Pattern Anal. Mach. Intell. 30, 328\u2013341 (2008)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"7_CR30","doi-asserted-by":"crossref","unstructured":"Yang, G., Manela, J., Happold, M., Ramanan, D.: Hierarchical deep stereo matching on high-resolution images. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5515\u20135524. IEEE (2019)","DOI":"10.1109\/CVPR.2019.00566"},{"key":"7_CR31","doi-asserted-by":"crossref","unstructured":"Menze, M., Geiger, A.: Object scene flow for autonomous vehicles. In: Conference on Computer Vision and Pattern Recognition (2015)","DOI":"10.1109\/CVPR.2015.7298925"},{"key":"7_CR32","unstructured":"Paszke, A., et al.: PyTorch: an imperative style, high-performance deep learning library. In: Advances in Neural Information Processing Systems, pp. 8024\u20138035 (2019)"},{"key":"7_CR33","doi-asserted-by":"crossref","unstructured":"Geiger, A., Lenz, P., Urtasun, R.: Are we ready for autonomous driving? The KITTI vision benchmark suite. In: Conference on Computer Vision and Pattern Recognition (2012)","DOI":"10.1109\/CVPR.2012.6248074"},{"key":"7_CR34","doi-asserted-by":"crossref","unstructured":"Gaidon, A., Wang, Q., Cabon, Y., Vig, E.: Virtual worlds as proxy for multi-object tracking analysis. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. IEEE (2016)","DOI":"10.1109\/CVPR.2016.470"},{"key":"7_CR35","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 Conference on Computer Vision and Pattern Recognition, pp. 3273\u20133282. IEEE (2019)","DOI":"10.1109\/CVPR.2019.00339"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ACCV 2020"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-69525-5_7","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,24]],"date-time":"2024-08-24T22:56:44Z","timestamp":1724540204000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-030-69525-5_7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"ISBN":["9783030695248","9783030695255"],"references-count":35,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-69525-5_7","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021]]},"assertion":[{"value":"27 February 2021","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ACCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Asian Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Kyoto","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Japan","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2020","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"30 November 2020","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 December 2020","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"15","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"accv2020","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/accv2020.kyoto\/","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":"Microsoft CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"768","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":"254","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":"33% - 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":"3","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)"}},{"value":"The conference was held virtually.","order":10,"name":"additional_info_on_review_process","label":"Additional Info on Review Process","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}