{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,28]],"date-time":"2026-05-28T02:08:00Z","timestamp":1779934080101,"version":"3.53.1"},"reference-count":38,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2025,2,22]],"date-time":"2025-02-22T00:00:00Z","timestamp":1740182400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,2,22]],"date-time":"2025-02-22T00:00:00Z","timestamp":1740182400000},"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":["SIViP"],"published-print":{"date-parts":[[2025,4]]},"DOI":"10.1007\/s11760-025-03908-z","type":"journal-article","created":{"date-parts":[[2025,2,22]],"date-time":"2025-02-22T09:19:07Z","timestamp":1740215947000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Real-time stereo matching via multi-volume attention concatenation volume"],"prefix":"10.1007","volume":"19","author":[{"given":"Zhongjian","family":"Lu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Langwen","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"An","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hongxia","family":"Gao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,2,22]]},"reference":[{"key":"3908_CR1","doi-asserted-by":"crossref","unstructured":"Mayer, N., Ilg, E., H\u00e4usser, 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: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 4040\u20134048 (2016)","DOI":"10.1109\/CVPR.2016.438"},{"key":"3908_CR2","doi-asserted-by":"crossref","unstructured":"Khamis, S., Fanello, S., Rhemann, C., Kowdle, A., Valentin, J., Izadi, S.: Stereonet: guided hierarchical refinement for real-time edge-aware depth prediction. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) Computer Vision\u2014ECCV 2018, pp. 596\u2013613. Springer, Cham (2018)","DOI":"10.1007\/978-3-030-01267-0_35"},{"key":"3908_CR3","doi-asserted-by":"crossref","unstructured":"Wang, Y., Lai, Z., Huang, G., Wang, B.H., van\u00a0der Maaten, L., Campbell, M., Weinberger, K.Q.: Anytime stereo image depth estimation on mobile devices. In: 2019 International Conference on Robotics and Automation (ICRA), pp. 5893\u20135900 (2019)","DOI":"10.1109\/ICRA.2019.8794003"},{"key":"3908_CR4","doi-asserted-by":"crossref","unstructured":"Chabra, R., Straub, J., Sweeney, C., Newcombe, R., Fuchs, H.: Stereodrnet: dilated residual stereonet. In: 2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 11778\u201311787 (2019)","DOI":"10.1109\/CVPR.2019.01206"},{"key":"3908_CR5","doi-asserted-by":"crossref","unstructured":"Tankovich, V., H\u00e4ne, C., Zhang, Y., Kowdle, A., Fanello, S., Bouaziz, S.: Hitnet: hierarchical iterative tile refinement network for real-time stereo matching. In: 2021 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 14357\u201314367 (2021)","DOI":"10.1109\/CVPR46437.2021.01413"},{"key":"3908_CR6","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: 2017 IEEE International Conference on Computer Vision (ICCV), pp. 66\u201375 (2017)","DOI":"10.1109\/ICCV.2017.17"},{"key":"3908_CR7","doi-asserted-by":"crossref","unstructured":"Guo, X., Yang, K., Yang, W., Wang, X., Li, H.: Group-wise correlation stereo network. In: 2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3268\u20133277 (2019)","DOI":"10.1109\/CVPR.2019.00339"},{"key":"3908_CR8","doi-asserted-by":"crossref","unstructured":"Lazebnik, S., Schmid, C., Ponce, J.: Beyond bags of features: spatial pyramid matching for recognizing natural scene categories. In: 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR\u201906), vol. 2, 2169\u20132178 (2006)","DOI":"10.1109\/CVPR.2006.68"},{"key":"3908_CR9","doi-asserted-by":"crossref","unstructured":"Zhao, H., Shi, J., Qi, X., Wang, X., Jia, J.: Pyramid scene parsing network. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 6230\u20136239 (2017)","DOI":"10.1109\/CVPR.2017.660"},{"issue":"3","key":"3908_CR10","doi-asserted-by":"crossref","first-page":"3448","DOI":"10.1109\/TITS.2022.3228042","volume":"24","author":"H Pan","year":"2023","unstructured":"Pan, H., Hong, Y., Sun, W., Jia, Y.: Deep dual-resolution networks for real-time and accurate semantic segmentation of traffic scenes. IEEE Trans. Intell. Transp. Syst. 24(3), 3448\u20133460 (2023)","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"3908_CR11","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":"3908_CR12","doi-asserted-by":"crossref","first-page":"59","DOI":"10.1038\/nn986","volume":"6","author":"M Menz","year":"2003","unstructured":"Menz, M., Freeman, R.: Stereoscopic depth processing in the visual cortex: a coarse-to-fine mechanism. Nat. Neurosci. 6, 59\u201365 (2003)","journal-title":"Nat. Neurosci."},{"issue":"5","key":"3908_CR13","doi-asserted-by":"crossref","first-page":"965","DOI":"10.1109\/TCSVT.2015.2513663","volume":"27","author":"K Zhang","year":"2017","unstructured":"Zhang, K., Fang, Y., Min, D., Sun, L., Yang, S., Yan, S.: Cross-scale cost aggregation for stereo matching. IEEE Trans. Circuits Syst. Video Technol. 27(5), 965\u2013976 (2017)","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"3908_CR14","doi-asserted-by":"crossref","unstructured":"Xu, H., Zhang, J.: Aanet: adaptive aggregation network for efficient stereo matching. In: 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1956\u20131965 (2020)","DOI":"10.1109\/CVPR42600.2020.00203"},{"key":"3908_CR15","doi-asserted-by":"crossref","unstructured":"Sandler, M., Howard, A., Zhu, M., Zhmoginov, A., Chen, L.-C.: Mobilenetv2: inverted residuals and linear bottlenecks. In: 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4510\u20134520 (2018)","DOI":"10.1109\/CVPR.2018.00474"},{"key":"3908_CR16","doi-asserted-by":"crossref","unstructured":"Deng, J., Dong, W., Socher, R., Li, L.-J., Li, K., Fei-Fei, L.: Imagenet: a large-scale hierarchical image database. In: 2009 IEEE Conference on Computer Vision and Pattern Recognition, pp. 248\u2013255 (2009)","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"3908_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":"3908_CR18","doi-asserted-by":"crossref","unstructured":"Menze, M., Geiger, A.: Object scene flow for autonomous vehicles. In: 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3061\u20133070 (2015)","DOI":"10.1109\/CVPR.2015.7298925"},{"key":"3908_CR19","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: Jiang, X., Hornegger, J., Koch, R. (eds.) Pattern Recognition, pp. 31\u201342. Springer, Cham (2014)","DOI":"10.1007\/978-3-319-11752-2_3"},{"issue":"1","key":"3908_CR20","doi-asserted-by":"crossref","first-page":"300","DOI":"10.1109\/TPAMI.2019.2928550","volume":"43","author":"Z Liang","year":"2021","unstructured":"Liang, Z., Guo, Y., Feng, Y., Chen, W., Qiao, L., Zhou, L., Zhang, J., Liu, H.: Stereo matching using multi-level cost volume and multi-scale feature constancy. IEEE Trans. Pattern Anal. Mach. Intell. 43(1), 300\u2013315 (2021)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"3908_CR21","doi-asserted-by":"crossref","unstructured":"Chang, J.-R., Chen, Y.-S.: Pyramid stereo matching network. In: 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5410\u20135418 (2018)","DOI":"10.1109\/CVPR.2018.00567"},{"key":"3908_CR22","doi-asserted-by":"crossref","unstructured":"Duggal, S., Wang, S., Ma, W.-C., Hu, R., Urtasun, R.: Deeppruner: learning efficient stereo matching via differentiable patchmatch. In: 2019 IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 4383\u20134392 (2019)","DOI":"10.1109\/ICCV.2019.00448"},{"key":"3908_CR23","doi-asserted-by":"crossref","unstructured":"Xu, G., Cheng, J., Guo, P., Yang, X.: Attention concatenation volume for accurate and efficient stereo matching. In: 2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 12971\u201312980 (2022)","DOI":"10.1109\/CVPR52688.2022.01264"},{"key":"3908_CR24","doi-asserted-by":"crossref","unstructured":"Song, X., Zhao, X., Hu, H., Fang, L.: Edgestereo: a context integrated residual pyramid network for stereo matching. In: Jawahar, C., Li, H., Mori, G., Schindler, K. (eds.) Computer Vision\u2014ACCV 2018, pp. 20\u201335. Springer, Cham (2019)","DOI":"10.1007\/978-3-030-20873-8_2"},{"key":"3908_CR25","doi-asserted-by":"crossref","unstructured":"Wang, F., Galliani, S., Vogel, C., Pollefeys, M.: Itermvs: iterative probability estimation for efficient multi-view stereo. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 8606\u20138615 (2022)","DOI":"10.1109\/CVPR52688.2022.00841"},{"key":"3908_CR26","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: 2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 185\u2013194 (2019)","DOI":"10.1109\/CVPR.2019.00027"},{"key":"3908_CR27","doi-asserted-by":"crossref","unstructured":"Shen, Z., Dai, Y., Rao, Z.: Cfnet: cascade and fused cost volume for robust stereo matching. In: 2021 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 13901\u201313910 (2021)","DOI":"10.1109\/CVPR46437.2021.01369"},{"key":"3908_CR28","doi-asserted-by":"crossref","unstructured":"Xu, G., Wang, X., Ding, X., Yang, X.: Iterative geometry encoding volume for stereo matching. In: 2023 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 21919\u201321928 (2023)","DOI":"10.1109\/CVPR52729.2023.02099"},{"key":"3908_CR29","unstructured":"Cheng, X., Zhong, Y., Harandi, M., Dai, Y., Chang, X., Li, H., Drummond, T., Ge, Z.: Hierarchical neural architecture search for deep stereo matching. In: Larochelle, H., Ranzato, M., Hadsell, R., Balcan, M., Lin, H. (eds.) Advances in Neural Information Processing Systems, vol.\u00a033, pp. 22158\u201322169. Curran Associates, Inc. (2020)"},{"key":"3908_CR30","doi-asserted-by":"crossref","unstructured":"Liu, Z., Li, Y., Okutomi, M.: Global occlusion-aware transformer for robust stereo matching. In: 2024 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV), pp. 3523\u20133532 (2024)","DOI":"10.1109\/WACV57701.2024.00350"},{"key":"3908_CR31","doi-asserted-by":"crossref","unstructured":"Xu, B., Xu, Y., Yang, X., Jia, W., Guo, Y.: Bilateral grid learning for stereo matching networks. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 12497\u201312506 (2021)","DOI":"10.1109\/CVPR46437.2021.01231"},{"key":"3908_CR32","doi-asserted-by":"crossref","unstructured":"Yao, C., Jia, Y., Di, H., Li, P., Wu, Y.: A decomposition model for stereo matching. In: 2021 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 6087\u20136096 (2021)","DOI":"10.1109\/CVPR46437.2021.00603"},{"key":"3908_CR33","doi-asserted-by":"crossref","unstructured":"Pan, B., Jiao, J., Pang, J., Cheng, J.: Distill-then-prune: An efficient compression framework for real-time stereo matching network on edge devices. In: 2024 IEEE International Conference on Robotics and Automation (ICRA), pp. 15113\u201315120 (2024)","DOI":"10.1109\/ICRA57147.2024.10611085"},{"key":"3908_CR34","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Chen, Y., Bai, X., Zhou, J., Yu, K., Li, Z., Yang, K.: Adaptive unimodal cost volume filtering for deep stereo matching. In: AAAI Conference on Artificial Intelligence (2019)","DOI":"10.1609\/aaai.v34i07.6991"},{"key":"3908_CR35","doi-asserted-by":"crossref","first-page":"910","DOI":"10.1007\/s11263-019-01287-w","volume":"128","author":"X Song","year":"2019","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 (2019)","journal-title":"Int. J. Comput. Vis."},{"issue":"10","key":"3908_CR36","doi-asserted-by":"crossref","first-page":"2361","DOI":"10.1109\/TPAMI.2019.2947374","volume":"42","author":"X Cheng","year":"2020","unstructured":"Cheng, X., Wang, P., Yang, R.: Learning depth with convolutional spatial propagation network. IEEE Trans. Pattern Anal. Mach. Intell. 42(10), 2361\u20132379 (2020)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"3908_CR37","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 (CVPR), pp. 16263\u201316272 (2022)","DOI":"10.1109\/CVPR52688.2022.01578"},{"key":"3908_CR38","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"}],"container-title":["Signal, Image and Video Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11760-025-03908-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11760-025-03908-z\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11760-025-03908-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,4,2]],"date-time":"2025-04-02T01:12:29Z","timestamp":1743556349000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11760-025-03908-z"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,2,22]]},"references-count":38,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2025,4]]}},"alternative-id":["3908"],"URL":"https:\/\/doi.org\/10.1007\/s11760-025-03908-z","relation":{},"ISSN":["1863-1703","1863-1711"],"issn-type":[{"value":"1863-1703","type":"print"},{"value":"1863-1711","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,2,22]]},"assertion":[{"value":"2 July 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"16 November 2024","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"31 January 2025","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"22 February 2025","order":4,"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 Conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}],"article-number":"328"}}