{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,13]],"date-time":"2026-05-13T17:44:26Z","timestamp":1778694266586,"version":"3.51.4"},"publisher-location":"Cham","reference-count":32,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031533075","type":"print"},{"value":"9783031533082","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024]]},"DOI":"10.1007\/978-3-031-53308-2_29","type":"book-chapter","created":{"date-parts":[[2024,1,27]],"date-time":"2024-01-27T21:37:36Z","timestamp":1706391456000},"page":"394-408","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["CT-MVSNet: Efficient Multi-view Stereo with\u00a0Cross-Scale Transformer"],"prefix":"10.1007","author":[{"given":"Sicheng","family":"Wang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hao","family":"Jiang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lei","family":"Xiang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,1,28]]},"reference":[{"issue":"2","key":"29_CR1","doi-asserted-by":"publisher","first-page":"153","DOI":"10.1007\/s11263-016-0902-9","volume":"120","author":"H Aan\u00e6s","year":"2016","unstructured":"Aan\u00e6s, H., Jensen, R.R., Vogiatzis, G., Tola, E., Dahl, A.B.: Large-scale data for multiple-view stereopsis. Int. J. Comput. Vis. 120(2), 153\u2013168 (2016)","journal-title":"Int. J. Comput. Vis."},{"key":"29_CR2","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"766","DOI":"10.1007\/978-3-540-88682-2_58","volume-title":"Computer Vision \u2013 ECCV 2008","author":"NDF Campbell","year":"2008","unstructured":"Campbell, N.D.F., Vogiatzis, G., Hern\u00e1ndez, C., Cipolla, R.: Using multiple hypotheses to improve depth-maps for multi-view stereo. In: Forsyth, D., Torr, P., Zisserman, A. (eds.) ECCV 2008. LNCS, vol. 5302, pp. 766\u2013779. Springer, Heidelberg (2008). https:\/\/doi.org\/10.1007\/978-3-540-88682-2_58"},{"key":"29_CR3","doi-asserted-by":"crossref","unstructured":"Cheng, S., et al.: Deep stereo using adaptive thin volume representation with uncertainty awareness. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2524\u20132534 (2020)","DOI":"10.1109\/CVPR42600.2020.00260"},{"key":"29_CR4","doi-asserted-by":"crossref","unstructured":"Ding, Y., et al.: TransMVSNet: global context-aware multi-view stereo network with transformers. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 8585\u20138594 (2022)","DOI":"10.1109\/CVPR52688.2022.00839"},{"key":"29_CR5","unstructured":"Dosovitskiy, A., et al.: An image is worth 16$$\\,\\times $$ 16 words: transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)"},{"key":"29_CR6","doi-asserted-by":"crossref","unstructured":"Galliani, S., Lasinger, K., Schindler, K.: Massively parallel multiview stereopsis by surface normal diffusion. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 873\u2013881 (2015)","DOI":"10.1109\/ICCV.2015.106"},{"key":"29_CR7","doi-asserted-by":"crossref","unstructured":"Gu, X., Fan, Z., Zhu, S., Dai, Z., Tan, F., Tan, P.: Cascade cost volume for high-resolution multi-view stereo and stereo matching. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2495\u20132504 (2020)","DOI":"10.1109\/CVPR42600.2020.00257"},{"key":"29_CR8","unstructured":"Katharopoulos, A., Vyas, A., Pappas, N., Fleuret, F.: Transformers are RNNs: fast autoregressive transformers with linear attention. In: Proceedings of International Conference on Machine Learning, pp. 5156\u20135165 (2020)"},{"issue":"4","key":"29_CR9","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3072959.3073599","volume":"36","author":"A Knapitsch","year":"2017","unstructured":"Knapitsch, A., Park, J., Zhou, Q.Y., Koltun, V.: Tanks and temples: benchmarking large-scale scene reconstruction. ACM Trans. Graph. (ToG) 36(4), 1\u201313 (2017)","journal-title":"ACM Trans. Graph. (ToG)"},{"key":"29_CR10","first-page":"8564","volume":"35","author":"J Liao","year":"2022","unstructured":"Liao, J., et al.: WT-MVSNet: window-based transformers for multi-view stereo. Adv. Neural. Inf. Process. Syst. 35, 8564\u20138576 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"29_CR11","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., Doll\u00e1r, P., Girshick, R., He, K., Hariharan, B., Belongie, S.: Feature pyramid networks for object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2117\u20132125 (2017)","DOI":"10.1109\/CVPR.2017.106"},{"key":"29_CR12","doi-asserted-by":"crossref","unstructured":"Liu, Z., et al.: Swin transformer: hierarchical vision transformer using shifted windows. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 10012\u201310022 (2021)","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"29_CR13","doi-asserted-by":"crossref","unstructured":"Ma, X., Gong, Y., Wang, Q., Huang, J., Chen, L., Yu, F.: EPP-MVSNet: epipolar-assembling based depth prediction for multi-view stereo. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 5732\u20135740 (2021)","DOI":"10.1109\/ICCV48922.2021.00568"},{"key":"29_CR14","doi-asserted-by":"crossref","unstructured":"Mi, Z., Di, C., Xu, D.: Generalized binary search network for highly-efficient multi-view stereo. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 12991\u201313000 (2022)","DOI":"10.1109\/CVPR52688.2022.01265"},{"key":"29_CR15","doi-asserted-by":"crossref","unstructured":"Peng, R., Wang, R., Wang, Z., Lai, Y., Wang, R.: Rethinking depth estimation for multi-view stereo: a unified representation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 8645\u20138654 (2022)","DOI":"10.1109\/CVPR52688.2022.00845"},{"key":"29_CR16","doi-asserted-by":"crossref","unstructured":"Ruan, C., Zhang, Z., Jiang, H., Dang, J., Wu, L., Zhang, H.: Vector approximate message passing with sparse Bayesian learning for gaussian mixture prior. China Communications (2023)","DOI":"10.23919\/JCC.2023.00.005"},{"key":"29_CR17","doi-asserted-by":"crossref","unstructured":"Sarlin, P.E., DeTone, D., Malisiewicz, T., Rabinovich, A.: SuperGlue: learning feature matching with graph neural networks. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4938\u20134947 (2020)","DOI":"10.1109\/CVPR42600.2020.00499"},{"key":"29_CR18","doi-asserted-by":"crossref","unstructured":"Schonberger, J.L., Frahm, J.M.: Structure-from-motion revisited. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4104\u20134113 (2016)","DOI":"10.1109\/CVPR.2016.445"},{"key":"29_CR19","doi-asserted-by":"crossref","unstructured":"Stereopsis, R.M.: Accurate, dense, and robust multiview stereopsis. IEEE Trans. Pattern Anal. Mach. Intell. 32(8) (2010)","DOI":"10.1109\/TPAMI.2009.161"},{"key":"29_CR20","doi-asserted-by":"crossref","unstructured":"Sun, J., Shen, Z., Wang, Y., Bao, H., Zhou, X.: LoFTR: detector-free local feature matching with transformers. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 8922\u20138931 (2021)","DOI":"10.1109\/CVPR46437.2021.00881"},{"key":"29_CR21","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems, vol. 30 (2017)"},{"key":"29_CR22","doi-asserted-by":"crossref","unstructured":"Wang, F., Galliani, S., Vogel, C., Speciale, P., Pollefeys, M.: PatchmatchNet: learned multi-view patchmatch stereo. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 14194\u201314203 (2021)","DOI":"10.1109\/CVPR46437.2021.01397"},{"key":"29_CR23","doi-asserted-by":"crossref","unstructured":"Wang, Q., Zhang, J., Yang, K., Peng, K., Stiefelhagen, R.: MatchFormer: interleaving attention in transformers for feature matching. In: Proceedings of the Asian Conference on Computer Vision, pp. 2746\u20132762 (2022)","DOI":"10.1007\/978-3-031-26313-2_16"},{"key":"29_CR24","doi-asserted-by":"crossref","unstructured":"Wang, S., Li, B., Dai, Y.: Efficient multi-view stereo by iterative dynamic cost volume. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 8655\u20138664 (2022)","DOI":"10.1109\/CVPR52688.2022.00846"},{"key":"29_CR25","doi-asserted-by":"publisher","unstructured":"Wang, X., et al.: MVSTER: epipolar transformer for efficient multi-view stereo. In: Proceedings of the European Conference on Computer Vision, pp. 573\u2013591. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-19821-2_33","DOI":"10.1007\/978-3-031-19821-2_33"},{"key":"29_CR26","doi-asserted-by":"crossref","unstructured":"Wei, Z., Zhu, Q., Min, C., Chen, Y., Wang, G.: AA-RMVSNet: adaptive aggregation recurrent multi-view stereo network. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 6187\u20136196 (2021)","DOI":"10.1109\/ICCV48922.2021.00613"},{"key":"29_CR27","doi-asserted-by":"crossref","unstructured":"Xi, J., Shi, Y., Wang, Y., Guo, Y., Xu, K.: RayMVSNet: learning ray-based 1D implicit fields for accurate multi-view stereo. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 8595\u20138605 (2022)","DOI":"10.1109\/CVPR52688.2022.00840"},{"key":"29_CR28","doi-asserted-by":"crossref","unstructured":"Yang, J., Mao, W., Alvarez, J.M., Liu, M.: Cost volume pyramid based depth inference for multi-view stereo. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4877\u20134886 (2020)","DOI":"10.1109\/CVPR42600.2020.00493"},{"key":"29_CR29","doi-asserted-by":"crossref","unstructured":"Yang, Z., Ren, Z., Shan, Q., Huang, Q.: MVS2D: efficient multi-view stereo via attention-driven 2d convolutions. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 8574\u20138584 (2022)","DOI":"10.1109\/CVPR52688.2022.00838"},{"key":"29_CR30","doi-asserted-by":"crossref","unstructured":"Yao, Y., Luo, Z., Li, S., Fang, T., Quan, L.: MVSNet: depth inference for unstructured multi-view stereo. In: Proceedings of the European Conference on Computer Vision, pp. 767\u2013783 (2018)","DOI":"10.1007\/978-3-030-01237-3_47"},{"key":"29_CR31","doi-asserted-by":"crossref","unstructured":"Yao, Y., Luo, Z., Li, S., Shen, T., Fang, T., Quan, L.: Recurrent MVSNet for high-resolution multi-view stereo depth inference. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5525\u20135534 (2019)","DOI":"10.1109\/CVPR.2019.00567"},{"key":"29_CR32","doi-asserted-by":"crossref","unstructured":"Yao, Y., et al.: BlendedMVS: a large-scale dataset for generalized multi-view stereo networks. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 1790\u20131799 (2020)","DOI":"10.1109\/CVPR42600.2020.00186"}],"container-title":["Lecture Notes in Computer Science","MultiMedia Modeling"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-53308-2_29","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,9]],"date-time":"2024-11-09T09:58:23Z","timestamp":1731146303000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-53308-2_29"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"ISBN":["9783031533075","9783031533082"],"references-count":32,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-53308-2_29","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]},"assertion":[{"value":"28 January 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"MMM","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Multimedia Modeling","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Amsterdam","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"The Netherlands","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 January 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2 February 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"30","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"mmm2024","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":"ConfTool Pro","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"297","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":"112","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":"38% - 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":"3.2","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":"3.2","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)"}}]}}