{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,6]],"date-time":"2026-06-06T20:10:34Z","timestamp":1780776634322,"version":"3.54.1"},"reference-count":40,"publisher":"Springer Science and Business Media LLC","issue":"5","license":[{"start":{"date-parts":[[2024,8,12]],"date-time":"2024-08-12T00:00:00Z","timestamp":1723420800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,8,12]],"date-time":"2024-08-12T00:00:00Z","timestamp":1723420800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["52375026"],"award-info":[{"award-number":["52375026"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Multimedia Systems"],"published-print":{"date-parts":[[2024,10]]},"DOI":"10.1007\/s00530-024-01419-4","type":"journal-article","created":{"date-parts":[[2024,8,12]],"date-time":"2024-08-12T10:02:55Z","timestamp":1723456975000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Multi-level pyramid fusion for efficient stereo matching"],"prefix":"10.1007","volume":"30","author":[{"given":"Jiaqi","family":"Zhu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bin","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xinhua","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,8,12]]},"reference":[{"key":"1419_CR1","doi-asserted-by":"publisher","first-page":"601","DOI":"10.1016\/j.neucom.2021.12.052","volume":"492","author":"A Chong","year":"2022","unstructured":"Chong, A., Yin, H., Liu, Y., Wan, J., Liu, Z., Han, M.: Multi-hierarchy feature extraction and multi-step cost aggregation for stereo matching. Neurocomputing 492, 601\u2013611 (2022)","journal-title":"Neurocomputing"},{"issue":"7","key":"1419_CR2","doi-asserted-by":"publisher","first-page":"1651","DOI":"10.1109\/TMI.2022.3147414","volume":"41","author":"W Xia","year":"2022","unstructured":"Xia, W., Chen, E.C., Pautler, S., Peters, T.M.: A robust edge-preserving stereo matching method for laparoscopic images. IEEE Trans. Med. Imaging 41(7), 1651\u20131664 (2022)","journal-title":"IEEE Trans. Med. Imaging"},{"key":"1419_CR3","doi-asserted-by":"crossref","unstructured":"Zhang, C., Li, Z., Cheng, Y., Cai, R., Chao, H., Rui, Y.: Meshstereo: A global stereo model with mesh alignment regularization for view interpolation. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2057\u20132065 (2015)","DOI":"10.1109\/ICCV.2015.238"},{"key":"1419_CR4","doi-asserted-by":"publisher","first-page":"7","DOI":"10.1023\/A:1014573219977","volume":"47","author":"D Scharstein","year":"2002","unstructured":"Scharstein, D., Szeliski, R.: A taxonomy and evaluation of dense two-frame stereo correspondence algorithms. Int. J. Comput. Vision 47, 7\u201342 (2002)","journal-title":"Int. J. Comput. Vision"},{"key":"1419_CR5","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":"1419_CR6","doi-asserted-by":"crossref","unstructured":"Weber, M., Humenberger, M., Kubinger, W.: A very fast census-based stereo matching implementation on a graphics processing unit. In: 2009 IEEE 12th International Conference on Computer Vision Workshops, ICCV Workshops, pp. 786\u2013793 (2009)","DOI":"10.1109\/ICCVW.2009.5457622"},{"issue":"11","key":"1419_CR7","doi-asserted-by":"publisher","first-page":"2725","DOI":"10.1109\/TPAMI.2017.2766072","volume":"40","author":"T Taniai","year":"2017","unstructured":"Taniai, T., Matsushita, Y., Sato, Y., Naemura, T.: Continuous 3d label stereo matching using local expansion moves. IEEE Trans. Pattern Anal. Mach. Intell. 40(11), 2725\u20132739 (2017)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"1419_CR8","doi-asserted-by":"crossref","unstructured":"Hirschmuller, H.: Accurate and efficient stereo processing by semi-global matching and mutual information. In: 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp. 807\u2013814 (2005)","DOI":"10.1109\/CVPR.2005.56"},{"key":"1419_CR9","doi-asserted-by":"crossref","unstructured":"Kendall, A., Martirosyan, H., Dasgupta, S., Henry, P., Kennedy, R., Bachrach, A., Bry, A.: 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 (2017)","DOI":"10.1109\/ICCV.2017.17"},{"key":"1419_CR10","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"},{"key":"1419_CR11","doi-asserted-by":"crossref","unstructured":"Xu, G., Cheng, J., Guo, P., Yang, X.: Attention concatenation volume for accurate and efficient stereo matching. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 12981\u201312990 (2022)","DOI":"10.1109\/CVPR52688.2022.01264"},{"key":"1419_CR12","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 (2021)","DOI":"10.1109\/3DV53792.2021.00032"},{"key":"1419_CR13","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\/CVF International Conference on Computer Vision, pp. 7484\u20137493 (2019)","DOI":"10.1109\/ICCV.2019.00758"},{"key":"1419_CR14","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":"1419_CR15","doi-asserted-by":"crossref","unstructured":"Li, J., Wang, P., Xiong, P., Cai, T., Yan, Z., Yang, L., Liu, J., Fan, H., Liu, S.: Practical stereo matching via cascaded recurrent network with adaptive correlation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 16263\u201316272 (2022)","DOI":"10.1109\/CVPR52688.2022.01578"},{"key":"1419_CR16","doi-asserted-by":"crossref","unstructured":"Xu, G., Wang, X., Ding, X., Yang, X.: Iterative geometry encoding volume for stereo matching. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 21919\u201321928 (2023)","DOI":"10.1109\/CVPR52729.2023.02099"},{"key":"1419_CR17","doi-asserted-by":"crossref","unstructured":"Geiger, A., Lenz, P., Urtasun, R.: Are we ready for autonomous driving? the kitti vision benchmark suite. In: 2012 IEEE Conference on Computer Vision and Pattern Recognition, pp. 3354\u20133361 (2012)","DOI":"10.1109\/CVPR.2012.6248074"},{"key":"1419_CR18","doi-asserted-by":"crossref","unstructured":"Mayer, N., Ilg, E., Hausser, P., Fischer, P., Cremers, D., Dosovitskiy, A., Brox, T.: 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":"1419_CR19","doi-asserted-by":"crossref","unstructured":"Dosovitskiy, A., Fischer, P., Ilg, E., Hausser, P., Hazirbas, C., Golkov, V., Van Der\u00a0Smagt, P., Cremers, D., Brox, T.: Flownet: Learning optical flow with convolutional networks. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2758\u20132766 (2015)","DOI":"10.1109\/ICCV.2015.316"},{"key":"1419_CR20","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 (ECCV), pp. 636\u2013651 (2018)","DOI":"10.1007\/978-3-030-01234-2_39"},{"key":"1419_CR21","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":"1419_CR22","doi-asserted-by":"crossref","unstructured":"Bangunharcana, A., Cho, J.W., Lee, S., Kweon, I.S., Kim, K.-S., Kim, S.: Correlate-and-excite: Real-time stereo matching via guided cost volume excitation. In: 2021 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 3542\u20133548 (2021)","DOI":"10.1109\/IROS51168.2021.9635909"},{"key":"1419_CR23","unstructured":"Howard, A., Zhmoginov, A., Chen, L.-C., Sandler, M., Zhu, M.: Inverted residuals and linear bottlenecks: Mobile networks for classification, detection and segmentation. (2018)"},{"key":"1419_CR24","doi-asserted-by":"crossref","unstructured":"Ronneberger, O., Fischer, P., Brox, T.: U-net: Convolutional networks for biomedical image segmentation. In: Medical Image Computing and Computer-Assisted Intervention\u2013MICCAI 2015: 18th International Conference, pp. 234\u2013241 (2015)","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"1419_CR25","doi-asserted-by":"crossref","unstructured":"Ruan, D., Wang, D., Zheng, Y., Zheng, N., Zheng, M.: Gaussian context transformer. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 15129\u201315138 (2021)","DOI":"10.1109\/CVPR46437.2021.01488"},{"key":"1419_CR26","doi-asserted-by":"crossref","unstructured":"Woo, S., Park, J., Lee, J.-Y., Kweon, I.S.: Cbam: Convolutional block attention module. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 3\u201319 (2018)","DOI":"10.1007\/978-3-030-01234-2_1"},{"key":"1419_CR27","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":"1419_CR28","doi-asserted-by":"crossref","unstructured":"Scharstein, D., Hirschm\u00fcller, H., Kitajima, Y., Krathwohl, G., Ne\u0161i\u0107, N., Wang, X., Westling, P.: High-resolution stereo datasets with subpixel-accurate ground truth. In: Pattern Recognition: 36th German Conference, pp. 31\u201342 (2014)","DOI":"10.1007\/978-3-319-11752-2_3"},{"key":"1419_CR29","doi-asserted-by":"crossref","unstructured":"Schops, T., Schonberger, J.L., Galliani, S., Sattler, T., Schindler, K., Pollefeys, M., Geiger, A.: A multi-view stereo benchmark with high-resolution images and multi-camera videos. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3260\u20133269 (2017)","DOI":"10.1109\/CVPR.2017.272"},{"key":"1419_CR30","doi-asserted-by":"crossref","unstructured":"Zeng, J., Yao, C., Yu, L., Wu, Y., Jia, Y.: Parameterized cost volume for stereo matching. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 18301\u201318311 (2023)","DOI":"10.1109\/ICCV51070.2023.01682"},{"key":"1419_CR31","doi-asserted-by":"publisher","first-page":"5835","DOI":"10.1109\/TIP.2021.3088635","volume":"30","author":"Y Deng","year":"2021","unstructured":"Deng, Y., Xiao, J., Zhou, S.Z., Feng, J.: Detail preserving coarse-to-fine matching for stereo matching and optical flow. IEEE Trans. Image Process. 30, 5835\u20135847 (2021)","journal-title":"IEEE Trans. Image Process."},{"issue":"3","key":"1419_CR32","doi-asserted-by":"publisher","first-page":"4353","DOI":"10.1109\/LRA.2021.3068108","volume":"6","author":"H Wang","year":"2021","unstructured":"Wang, H., Fan, R., Cai, P., Liu, M.: Pvstereo: pyramid voting module for end-to-end self-supervised stereo matching. IEEE Robotics Autom Lett 6(3), 4353\u20134360 (2021)","journal-title":"IEEE Robotics Autom Lett"},{"key":"1419_CR33","doi-asserted-by":"crossref","unstructured":"Tankovich, V., Hane, C., Zhang, Y., Kowdle, A., Fanello, S., Bouaziz, S.: Hitnet: Hierarchical iterative tile refinement network for real-time stereo matching. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 14362\u201314372 (2021)","DOI":"10.1109\/CVPR46437.2021.01413"},{"key":"1419_CR34","doi-asserted-by":"crossref","unstructured":"Wang, X., Xu, G., Jia, H., Yang, X.: Selective-stereo: Adaptive frequency information selection for stereo matching. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 19701\u201319710 (2024)","DOI":"10.1109\/CVPR52733.2024.01863"},{"key":"1419_CR35","doi-asserted-by":"crossref","unstructured":"Xu, P., Xiang, Z., Qiao, C., Fu, J., Pu, T.: Adaptive multi-modal cross-entropy loss for stereo matching. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5135\u20135144 (2024)","DOI":"10.1109\/CVPR52733.2024.00491"},{"key":"1419_CR36","doi-asserted-by":"crossref","unstructured":"Shen, Z., Dai, Y., Rao, Z.: Cfnet: Cascade and fused cost volume for robust stereo matching. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 13906\u201313915 (2021)","DOI":"10.1109\/CVPR46437.2021.01369"},{"key":"1419_CR37","doi-asserted-by":"crossref","unstructured":"Shen, Z., Dai, Y., Song, X., Rao, Z., Zhou, D., Zhang, L.: Pcw-net: pyramid combination and warping cost volume for stereo matching. In: European Conference on Computer Vision, pp. 280\u2013297 (2022)","DOI":"10.1007\/978-3-031-19824-3_17"},{"key":"1419_CR38","doi-asserted-by":"crossref","unstructured":"Liu, H., Lu, T., Xu, Y., Liu, J., Li, W., Chen, L.: Camliflow: bidirectional camera-lidar fusion for joint optical flow and scene flow estimation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5791\u20135801 (2022)","DOI":"10.1109\/CVPR52688.2022.00570"},{"key":"1419_CR39","doi-asserted-by":"crossref","unstructured":"Zeng, K., Zhang, H., Wang, W., Wang, Y., Mao, J.: Deep stereo network with mrf-based cost aggregation. IEEE Transactions on Circuits and Systems for Video Technology (2023)","DOI":"10.1109\/TCSVT.2023.3312153"},{"key":"1419_CR40","doi-asserted-by":"crossref","unstructured":"Zhang, J., Wang, X., Bai, X., Wang, C., Huang, L., Chen, Y., Gu, L., Zhou, J., Harada, T., Hancock, E.R.: Revisiting domain generalized stereo matching networks from a feature consistency perspective. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 13001\u201313011 (2022)","DOI":"10.1109\/CVPR52688.2022.01266"}],"container-title":["Multimedia Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00530-024-01419-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00530-024-01419-4\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00530-024-01419-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,28]],"date-time":"2024-10-28T18:07:28Z","timestamp":1730138848000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00530-024-01419-4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,8,12]]},"references-count":40,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2024,10]]}},"alternative-id":["1419"],"URL":"https:\/\/doi.org\/10.1007\/s00530-024-01419-4","relation":{},"ISSN":["0942-4962","1432-1882"],"issn-type":[{"value":"0942-4962","type":"print"},{"value":"1432-1882","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,8,12]]},"assertion":[{"value":"24 January 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"15 July 2024","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"12 August 2024","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}],"article-number":"239"}}