{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,4,9]],"date-time":"2025-04-09T04:25:31Z","timestamp":1744172731547,"version":"3.40.3"},"reference-count":40,"publisher":"Springer Science and Business Media LLC","issue":"5","license":[{"start":{"date-parts":[[2025,3,10]],"date-time":"2025-03-10T00:00:00Z","timestamp":1741564800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,3,10]],"date-time":"2025-03-10T00:00:00Z","timestamp":1741564800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"name":"the Central Universities","award":["2022JBQY009"],"award-info":[{"award-number":["2022JBQY009"]}]},{"name":"National Key R&D Program ''Transportation Infrastructure'' \"Reveal the list and take comman'' project","award":["2022YFB2603302"],"award-info":[{"award-number":["2022YFB2603302"]}]},{"DOI":"10.13039\/501100001809","name":"National Nature Science Foundation of China","doi-asserted-by":"crossref","award":["51827813"],"award-info":[{"award-number":["51827813"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["SIViP"],"published-print":{"date-parts":[[2025,5]]},"DOI":"10.1007\/s11760-025-03985-0","type":"journal-article","created":{"date-parts":[[2025,3,10]],"date-time":"2025-03-10T09:14:18Z","timestamp":1741598058000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["SP-A$$\\text {I}^{2}$$: sparse prior guided cost construction and adaptive intra and inter scale cost aggregation for multi-view depth estimation"],"prefix":"10.1007","volume":"19","author":[{"given":"Qianqian","family":"Du","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hui","family":"Yin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ming","family":"Han","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,3,10]]},"reference":[{"key":"3985_CR1","doi-asserted-by":"publisher","unstructured":"Campbell, N.D., Vogiatzis, G., Hern\u00e1ndez, C., Cipolla, R.: Using multiple hypotheses to improve depth-maps for multi-view stereo. In: European Conference on Computer Vision, pp. 766\u2013779 (2008). https:\/\/doi.org\/10.1007\/978-3-540-88682-2_58","DOI":"10.1007\/978-3-540-88682-2_58"},{"key":"3985_CR2","doi-asserted-by":"publisher","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). https:\/\/doi.org\/10.1109\/ICCV.2015.106","DOI":"10.1109\/ICCV.2015.106"},{"key":"3985_CR3","doi-asserted-by":"publisher","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). https:\/\/doi.org\/10.1109\/CVPR42600.2020.00257","DOI":"10.1109\/CVPR42600.2020.00257"},{"key":"3985_CR4","doi-asserted-by":"publisher","unstructured":"Cheng, S., Xu, Z., Zhu, S., Li, Z., Li, L.E., Ramamoorthi, R., Su, H.: 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). https:\/\/doi.org\/10.1109\/CVPR42600.2020.00260","DOI":"10.1109\/CVPR42600.2020.00260"},{"key":"3985_CR5","doi-asserted-by":"publisher","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). https:\/\/doi.org\/10.1109\/CVPR42600.2020.00203","DOI":"10.1109\/CVPR42600.2020.00203"},{"issue":"1","key":"3985_CR6","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s11760-024-03720-1","volume":"19","author":"I Ardiyanto","year":"2025","unstructured":"Ardiyanto, I., Al-Fahsi, R.D.H.: Lightweight monocular depth estimation network for robotics using intercept block ghostnet. Signal, Image and Video Processing 19(1), 1\u201314 (2025). https:\/\/doi.org\/10.1007\/s11760-024-03720-1","journal-title":"Signal, Image and Video Processing"},{"issue":"4","key":"3985_CR7","doi-asserted-by":"publisher","first-page":"991","DOI":"10.1007\/S11760-022-02303-2","volume":"17","author":"Z Xie","year":"2023","unstructured":"Xie, Z., Zhou, S., Zheng, M., Pei, F.: Research on self-supervised depth estimation algorithm of driving scene based on monocular vision. Signal, Image and Video Processing 17(4), 991\u2013999 (2023). https:\/\/doi.org\/10.1007\/S11760-022-02303-2","journal-title":"Signal, Image and Video Processing"},{"key":"3985_CR8","doi-asserted-by":"publisher","unstructured":"Wu, J., Li, R., Xu, H., Zhao, W., Zhu, Y., Sun, J., Zhang, Y.: Gomvs: Geometrically consistent cost aggregation for multi-view stereo. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 20207\u201320216 (2024). https:\/\/doi.org\/10.1109\/CVPR52733.2024.01910","DOI":"10.1109\/CVPR52733.2024.01910"},{"key":"3985_CR9","unstructured":"Im, S., Jeon, H.-G., Lin, S., Kweon, I.S.: Dpsnet: End-to-end deep plane sweep stereo (2019). arXiv preprint arXiv:1905.00538"},{"key":"3985_CR10","doi-asserted-by":"publisher","unstructured":"Yao, Y., Luo, Z., Li, S., Fang, T., Quan, L.: Mvsnet: Depth inference for unstructured multi-view stereo. In: European Conference on Computer Vision, pp. 767\u2013783 (2018). https:\/\/doi.org\/10.1007\/978-3-030-01237-3_47","DOI":"10.1007\/978-3-030-01237-3_47"},{"key":"3985_CR11","doi-asserted-by":"publisher","unstructured":"Huang, P.-H., Matzen, K., Kopf, J., Ahuja, N.: Deepmvs: Learning multi-view stereopsis. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2821\u20132830 (2018). https:\/\/doi.org\/10.1109\/CVPR.2018.00298","DOI":"10.1109\/CVPR.2018.00298"},{"key":"3985_CR12","doi-asserted-by":"publisher","unstructured":"Kusupati, U., Cheng, S., Chen, R., Su, H.: Normal assisted stereo depth estimation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2189\u20132199 (2020). https:\/\/doi.org\/10.1109\/CVPR42600.2020.00226","DOI":"10.1109\/CVPR42600.2020.00226"},{"key":"3985_CR13","doi-asserted-by":"publisher","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). https:\/\/doi.org\/10.1109\/CVPR.2019.00567","DOI":"10.1109\/CVPR.2019.00567"},{"key":"3985_CR14","doi-asserted-by":"publisher","unstructured":"Zhang, X., Yang, F., Chang, M., Qin, X.: Mg-mvsnet: Multiple granularities feature fusion network for multi-view stereo. Neurocomputing 528, 35\u201347 (2023) https:\/\/doi.org\/10.1016\/J.NEUCOM.2023.01.062","DOI":"10.1016\/J.NEUCOM.2023.01.062"},{"key":"3985_CR15","doi-asserted-by":"publisher","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). https:\/\/doi.org\/10.1109\/CVPR46437.2021.01397","DOI":"10.1109\/CVPR46437.2021.01397"},{"key":"3985_CR16","doi-asserted-by":"publisher","unstructured":"Wang, X., Zhu, Z., Huang, G., Qin, F., Ye, Y., He, Y., Chi, X., Wang, X.: Mvster: Epipolar transformer for efficient multi-view stereo. In: European Conference on Computer Vision, pp. 573\u2013591 (2022). https:\/\/doi.org\/10.1007\/978-3-031-19821-2_33","DOI":"10.1007\/978-3-031-19821-2_33"},{"key":"3985_CR17","doi-asserted-by":"publisher","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). https:\/\/doi.org\/10.1109\/CVPR52688.2022.00845","DOI":"10.1109\/CVPR52688.2022.00845"},{"key":"3985_CR18","doi-asserted-by":"publisher","unstructured":"Weilharter, R., Fraundorfer, F.: Hammer: Learning entropy maps to create accurate 3d models in multi-view stereo. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 3466\u20133475 (2024). https:\/\/doi.org\/10.1109\/WACV57701.2024.00343","DOI":"10.1109\/WACV57701.2024.00343"},{"key":"3985_CR19","doi-asserted-by":"publisher","unstructured":"Donnelly, J., Barnett, A.J., Chen, C.: Deformable protopnet: An interpretable image classifier using deformable prototypes. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10265\u201310275 (2022). https:\/\/doi.org\/10.1109\/CVPR52688.2022.01002","DOI":"10.1109\/CVPR52688.2022.01002"},{"key":"3985_CR20","doi-asserted-by":"publisher","unstructured":"Wang, K., Shen, S.: Mvdepthnet: Real-time multiview depth estimation neural network. In: 2018 International Conference on 3d Vision (3DV), pp. 248\u2013257 (2018). https:\/\/doi.org\/10.1109\/3DV.2018.00037","DOI":"10.1109\/3DV.2018.00037"},{"key":"3985_CR21","doi-asserted-by":"publisher","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). https:\/\/doi.org\/10.1109\/TPAMI.2021.3082562","DOI":"10.1109\/TPAMI.2021.3082562"},{"key":"3985_CR22","doi-asserted-by":"publisher","unstructured":"Wei, Z., Zhu, Q., Min, C., Chen, Y.: Aa-rmvsnet: Adaptive aggregation recurrent multi-view stereo network. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 6187\u20136196 (2021). https:\/\/doi.org\/10.1109\/ICCV48922.2021.00613","DOI":"10.1109\/ICCV48922.2021.00613"},{"issue":"5","key":"3985_CR23","doi-asserted-by":"publisher","first-page":"1844","DOI":"10.1016\/J.PATCOG.2014.11.006","volume":"48","author":"M Pedersoli","year":"2015","unstructured":"Pedersoli, M., Vedaldi, A., Gonzalez, J., Roca, X.: A coarse-to-fine approach for fast deformable object detection. Pattern Recognition 48(5), 1844\u20131853 (2015). https:\/\/doi.org\/10.1016\/J.PATCOG.2014.11.006","journal-title":"Pattern Recognition"},{"key":"3985_CR24","doi-asserted-by":"crossref","unstructured":"Cui, Y., Tao, Y., Bing, Z., Ren, W., Gao, X., Cao, X., Huang, K., Knoll, A.: Selective frequency network for image restoration. In: Proceedings of the International Conference on Learning Representations (2023). https:\/\/openreview.net\/forum?id=tyZ1ChGZIKO","DOI":"10.1109\/ICCV51070.2023.01195"},{"key":"3985_CR25","doi-asserted-by":"publisher","unstructured":"Cui, Y., Ren, W., Cao, X., Knoll, A.: Focal network for image restoration. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 13001\u201313011 (2023). https:\/\/doi.org\/10.1109\/ICCV51070.2023.01195","DOI":"10.1109\/ICCV51070.2023.01195"},{"key":"3985_CR26","doi-asserted-by":"publisher","unstructured":"Cui, Y., Ren, W., Knoll, A.: Omni-kernel network for image restoration. In: Proceedings of the AAAI Conference on Artificial Intelligence, pp. 1426\u20131434 (2024). https:\/\/doi.org\/10.1609\/AAAI.V38I2.27907","DOI":"10.1609\/AAAI.V38I2.27907"},{"key":"3985_CR27","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3419007","author":"Y Cui","year":"2024","unstructured":"Cui, Y., Ren, W., Cao, X., Knoll, A.: Revitalizing convolutional network for image restoration. IEEE Transactions on Pattern Analysis and Machine Intelligence (2024). https:\/\/doi.org\/10.1109\/TPAMI.2024.3419007","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"3985_CR28","doi-asserted-by":"publisher","unstructured":"Li, J., Lu, Z., Wang, Y., Xiao, J., Wang, Y.: Nr-mvsnet: Learning multi-view stereo based on normal consistency and depth refinement. IEEE Transactions on Image Processing 32, 2649\u20132662 (2023) https:\/\/doi.org\/10.1109\/TIP.2023.3272170","DOI":"10.1109\/TIP.2023.3272170"},{"key":"3985_CR29","doi-asserted-by":"publisher","unstructured":"Song, S., Truong, K.G., Kim, D., Jo, S.: Prior depth-based multi-view stereo network for online 3d model reconstruction. Pattern Recognition 136, 109198 (2023) https:\/\/doi.org\/10.1016\/J.PATCOG.2022.109198","DOI":"10.1016\/J.PATCOG.2022.109198"},{"issue":"9","key":"3985_CR30","doi-asserted-by":"publisher","first-page":"1904","DOI":"10.1109\/TPAMI.2015.2389824","volume":"37","author":"K He","year":"2015","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Spatial pyramid pooling in deep convolutional networks for visual recognition. IEEE transactions on pattern analysis and machine intelligence 37(9), 1904\u20131916 (2015). https:\/\/doi.org\/10.1109\/TPAMI.2015.2389824","journal-title":"IEEE transactions on pattern analysis and machine intelligence"},{"key":"3985_CR31","doi-asserted-by":"publisher","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). https:\/\/doi.org\/10.1109\/CVPR.2016.445","DOI":"10.1109\/CVPR.2016.445"},{"key":"3985_CR32","doi-asserted-by":"publisher","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). https:\/\/doi.org\/10.1109\/ICCV.2017.17","DOI":"10.1109\/ICCV.2017.17"},{"key":"3985_CR33","doi-asserted-by":"publisher","unstructured":"Zhu, X., Hu, H., Lin, S., Dai, J.: Deformable convnets v2: More deformable, better results. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9308\u20139316 (2019). https:\/\/doi.org\/10.1109\/CVPR.2019.00953","DOI":"10.1109\/CVPR.2019.00953"},{"key":"3985_CR34","doi-asserted-by":"publisher","unstructured":"Xiao, J., Owens, A., Torralba, A.: Sun3d: A database of big spaces reconstructed using sfm and object labels. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1625\u20131632 (2013). https:\/\/doi.org\/10.1109\/ICCV.2013.458","DOI":"10.1109\/ICCV.2013.458"},{"key":"3985_CR35","doi-asserted-by":"publisher","unstructured":"Sturm, J., Engelhard, N., Endres, F.: A benchmark for the evaluation of rgb-d slam systems. In: 2012 IEEE\/RSJ International Conference on Intelligent Robots and Systems, pp. 573\u2013580 (2012). https:\/\/doi.org\/10.1109\/IROS.2012.6385773","DOI":"10.1109\/IROS.2012.6385773"},{"key":"3985_CR36","doi-asserted-by":"publisher","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). https:\/\/doi.org\/10.1109\/CVPR.2016.445","DOI":"10.1109\/CVPR.2016.445"},{"key":"3985_CR37","doi-asserted-by":"publisher","unstructured":"Shotton, J., Glocker, B., Zach, C., Izadi, S., Criminisi, A., Fitzgibbon, A.: Scene coordinate regression forests for camera relocalization in rgb-d images. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2930\u20132937 (2013). https:\/\/doi.org\/10.1109\/CVPR.2013.377","DOI":"10.1109\/CVPR.2013.377"},{"key":"3985_CR38","unstructured":"Cheng, K., Chen, H., Yin, W., Xu, G., Chen, X.: Exploiting correspondences with all-pairs correlations for multi-view depth estimation (2022). arXiv preprint arXiv:2205.02481"},{"key":"3985_CR39","doi-asserted-by":"publisher","unstructured":"Yifan, W., Doersch, C., Arandjelovi\u0107, R., Carreira, J., Zisserman, A.: Input-level inductive biases for 3d reconstruction. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 6176\u20136186 (2022). https:\/\/doi.org\/10.1109\/CVPR52688.2022.00608","DOI":"10.1109\/CVPR52688.2022.00608"},{"issue":"11","key":"3985_CR40","doi-asserted-by":"publisher","first-page":"13941","DOI":"10.1109\/TPAMI.2023.3298645","volume":"45","author":"H Xu","year":"2023","unstructured":"Xu, H., Zhang, J., Cai, J., Rezatofighi, H., Yu, F., Tao, D., Geiger, A.: Unifying flow, stereo and depth estimation. IEEE Transactions on Pattern Analysis and Machine Intelligence 45(11), 13941\u201313958 (2023). https:\/\/doi.org\/10.1109\/TPAMI.2023.3298645","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"}],"container-title":["Signal, Image and Video Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11760-025-03985-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11760-025-03985-0\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11760-025-03985-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,4,8]],"date-time":"2025-04-08T20:09:36Z","timestamp":1744142976000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11760-025-03985-0"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,3,10]]},"references-count":40,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2025,5]]}},"alternative-id":["3985"],"URL":"https:\/\/doi.org\/10.1007\/s11760-025-03985-0","relation":{},"ISSN":["1863-1703","1863-1711"],"issn-type":[{"type":"print","value":"1863-1703"},{"type":"electronic","value":"1863-1711"}],"subject":[],"published":{"date-parts":[[2025,3,10]]},"assertion":[{"value":"11 December 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"10 February 2025","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"22 February 2025","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"10 March 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 that they have no Conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}],"article-number":"393"}}