{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,14]],"date-time":"2026-10-14T16:34:33Z","timestamp":1791995673307,"version":"4.4.0"},"reference-count":78,"publisher":"Springer Science and Business Media LLC","issue":"6","license":[{"start":{"date-parts":[[2025,1,7]],"date-time":"2025-01-07T00:00:00Z","timestamp":1736208000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,1,7]],"date-time":"2025-01-07T00:00:00Z","timestamp":1736208000000},"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":["62176096"],"award-info":[{"award-number":["62176096"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61991412"],"award-info":[{"award-number":["61991412"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int J Comput Vis"],"published-print":{"date-parts":[[2025,6]]},"DOI":"10.1007\/s11263-024-02337-8","type":"journal-article","created":{"date-parts":[[2025,1,7]],"date-time":"2025-01-07T19:39:12Z","timestamp":1736278752000},"page":"3367-3391","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":10,"title":["Context-Aware Multi-view Stereo Network for Efficient Edge-Preserving Depth Estimation"],"prefix":"10.1007","volume":"133","author":[{"given":"Wanjuan","family":"Su","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3284-864X","authenticated-orcid":false,"given":"Wenbing","family":"Tao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,1,7]]},"reference":[{"issue":"2","key":"2337_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. (2016). Large-scale data for multiple-view stereopsis. International Journal of Computer Vision, 120(2), 153\u2013168.","journal-title":"International Journal of Computer Vision"},{"key":"2337_CR2","first-page":"20014","volume":"34","author":"A Ali","year":"2021","unstructured":"Ali, A., Touvron, H., Caron, M., Bojanowski, P., Douze, M., Joulin, A., Laptev, I., Neverova, N., Synnaeve, G., Verbeek, J., et al. (2021). Xcit: Cross-covariance image transformers. Advances in Neural Information Processing Systems, 34, 20014\u201320027.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"2337_CR3","doi-asserted-by":"crossref","unstructured":"Campbell, NDF, Vogiatzis, G, Hern\u00e1ndez, C, Cipolla, R. (2008). Using multiple hypotheses to improve depth-maps for multi-view stereo. In Proceedings of the European Conference on Computer Vision, pp. 766\u2013779. Springer","DOI":"10.1007\/978-3-540-88682-2_58"},{"key":"2337_CR4","unstructured":"Cao, Chenjie, Ren, Xinlin, Fu, Yanwei. (2022). Mvsformer: Multi-view stereo by learning robust image features and temperature-based depth. Transactions of Machine Learning Research, 1\u201329."},{"key":"2337_CR5","doi-asserted-by":"crossref","unstructured":"Caron, M., Touvron, H., Misra, I., J\u00e9gou, H., Mairal, J., Bojanowski, P., Joulin, A. (2021). Emerging properties in self-supervised vision transformers. In Proceedings of the IEEE\/CVF international conference on computer vision, pp. 9650\u20139660","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"2337_CR6","doi-asserted-by":"crossref","unstructured":"Cheng, S., Xu, Z., Zhu, S., Li, Z., Li, L. E., Ramamoorthi, R., Su, H. (2020). Deep stereo using adaptive thin volume representation with uncertainty awareness. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2524\u20132534.","DOI":"10.1109\/CVPR42600.2020.00260"},{"key":"2337_CR7","doi-asserted-by":"crossref","unstructured":"Collins, R. T. (1996). A space-sweep approach to true multi-image matching. In Proceedings CVPR IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp. 358\u2013363. IEEE","DOI":"10.1109\/CVPR.1996.517097"},{"key":"2337_CR8","doi-asserted-by":"crossref","unstructured":"Ding, Y., Yuan, W., Zhu, Q., Zhang, H., Liu, X., Wang, Y., Liu, X. (2022). 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.","DOI":"10.1109\/CVPR52688.2022.00839"},{"issue":"8","key":"2337_CR9","doi-asserted-by":"publisher","first-page":"1362","DOI":"10.1109\/TPAMI.2009.161","volume":"32","author":"Y Furukawa","year":"2010","unstructured":"Furukawa, Y., & Ponce, J. (2010). Accurate, dense, and robust multiview stereopsis. IEEE Transactions on Pattern Analysis and Machine Intelligence, 32(8), 1362\u20131376.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"2337_CR10","doi-asserted-by":"crossref","unstructured":"Galliani, S., Lasinger, K., Schindler, K. (2015). Massively parallel multiview stereopsis by surface normal diffusion. In Proceedings of the IEEE International Conference on Computer Vision, pp. 873\u2013881.","DOI":"10.1109\/ICCV.2015.106"},{"key":"2337_CR11","doi-asserted-by":"crossref","unstructured":"Gu, X., Fan, Z., Zhu, S., Dai, Z., Tan, F., Tan, P. (2020). Cascade cost volume for high-resolution multi-view stereo and stereo matching. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2495\u20132504.","DOI":"10.1109\/CVPR42600.2020.00257"},{"key":"2337_CR12","doi-asserted-by":"crossref","unstructured":"Guo, X., Yang, K., Yang, W., Wang, X., Li, H. (2019). Group-wise correlation stereo network. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 3273\u20133282","DOI":"10.1109\/CVPR.2019.00339"},{"key":"2337_CR13","doi-asserted-by":"crossref","unstructured":"Ji, M., Gall, J., Zheng, H., Liu, Y., Fang, L. (2017). Surfacenet: An end-to-end 3d neural network for multiview stereopsis. In Proceedings of the IEEE International Conference on Computer Vision, pp. 2307\u20132315.","DOI":"10.1109\/ICCV.2017.253"},{"key":"2337_CR14","doi-asserted-by":"crossref","unstructured":"Jiang, S., Campbell, D., Lu, Y., Li, H., Hartley, R. (2021). Learning to estimate hidden motions with global motion aggregation. In Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 9772\u20139781.","DOI":"10.1109\/ICCV48922.2021.00963"},{"key":"2337_CR15","doi-asserted-by":"crossref","unstructured":"Jiang, W., Trulls, E., Hosang, J., Tagliasacchi, A., Yi, K. M. (2021). Cotr: Correspondence transformer for matching across images. In Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 6207\u20136217.","DOI":"10.1109\/ICCV48922.2021.00615"},{"key":"2337_CR16","unstructured":"Katharopoulos, A., Vyas, A., Pappas, N., Fleuret, F. (2020). Transformers are rnns: Fast autoregressive transformers with linear attention. In International conference on machine learning, pp. 5156\u20135165. PMLR."},{"key":"2337_CR17","doi-asserted-by":"crossref","unstructured":"Kendall, A., Martirosyan, H., Dasgupta, S., Henry, P., Kennedy, R., Bachrach, A., Bry, A. (2017). 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.","DOI":"10.1109\/ICCV.2017.17"},{"key":"2337_CR18","doi-asserted-by":"crossref","unstructured":"Khamis, S., Fanello, S., Rhemann, C., Kowdle, A., Valentin, J., Izadi, S. (2018). Stereonet: Guided hierarchical refinement for real-time edge-aware depth prediction. In Proceedings of the European Conference on Computer Vision (ECCV), pp. 573\u2013590.","DOI":"10.1007\/978-3-030-01267-0_35"},{"issue":"2","key":"2337_CR19","doi-asserted-by":"publisher","first-page":"579","DOI":"10.1007\/s11263-020-01386-z","volume":"129","author":"B Kim","year":"2021","unstructured":"Kim, B., Ponce, J., & Ham, B. (2021). Deformable kernel networks for joint image filtering. International Journal of Computer Vision, 129(2), 579\u2013600.","journal-title":"International Journal of Computer Vision"},{"key":"2337_CR20","unstructured":"Kingma, D. P., & Ba, J. (2014). Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980,"},{"issue":"4","key":"2337_CR21","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. (2017). Tanks and temples: Benchmarking large-scale scene reconstruction. ACM Transactions on Graphics (ToG), 36(4), 1\u201313.","journal-title":"ACM Transactions on Graphics (ToG)"},{"key":"2337_CR22","doi-asserted-by":"crossref","unstructured":"Kuhn, A., Sormann, C., Rossi, M., Erdler, O., Fraundorfer, F. (2020). Deepc-mvs: Deep confidence prediction for multi-view stereo reconstruction. In Proceedings of the International Conference on 3D Vision, pp. 404\u2013413.","DOI":"10.1109\/3DV50981.2020.00050"},{"key":"2337_CR23","doi-asserted-by":"crossref","unstructured":"Li, Z., Liu, X., Drenkow, N., Ding, A., Creighton, F. X., Taylor, R. H., & Unberath, M. (2021). Revisiting stereo depth estimation from a sequence-to-sequence perspective with transformers. In Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 6197\u20136206.","DOI":"10.1109\/ICCV48922.2021.00614"},{"issue":"8","key":"2337_CR24","doi-asserted-by":"publisher","first-page":"1909","DOI":"10.1109\/TPAMI.2018.2890623","volume":"41","author":"Y Li","year":"2019","unstructured":"Li, Y., Huang, J.-B., Ahuja, N., & Yang, M.-H. (2019). Joint image filtering with deep convolutional networks. IEEE Transactions on Pattern Analysis and Machine Intelligence, 41(8), 1909\u20131923.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"2337_CR25","doi-asserted-by":"crossref","unstructured":"Lin, T.-Y., Doll\u00e1r, P., Girshick, R., He, K., Hariharan, B., Belongie, S. (2017). Feature pyramid networks for object detection. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2117\u20132125.","DOI":"10.1109\/CVPR.2017.106"},{"key":"2337_CR26","doi-asserted-by":"crossref","unstructured":"Luo, K., Guan, T., Ju, L., Huang, H., Luo, Y. (2019). P-mvsnet: Learning patch-wise matching confidence aggregation for multi-view stereo. In Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 10452\u201310461.","DOI":"10.1109\/ICCV.2019.01055"},{"key":"2337_CR27","doi-asserted-by":"crossref","unstructured":"Luo, K., Wang, C., Liu, S., Fan, H., Wang, J., Sun, J. (2021). Upflow: Upsampling pyramid for unsupervised optical flow learning. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 1045\u20131054.","DOI":"10.1109\/CVPR46437.2021.00110"},{"key":"2337_CR28","doi-asserted-by":"crossref","unstructured":"Ma, X., Gong, Y., Wang, Q., Huang, J., Chen, L., Yu, F. (2021). 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.","DOI":"10.1109\/ICCV48922.2021.00568"},{"key":"2337_CR29","doi-asserted-by":"crossref","unstructured":"Mi, Z., Di, C., Xu, D. (2022). 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.","DOI":"10.1109\/CVPR52688.2022.01265"},{"key":"2337_CR30","unstructured":"OpenMVS. (2015). open multi-view stereo reconstruction library. https:\/\/github.com\/cdcseacave\/openMVS."},{"key":"2337_CR31","unstructured":"Paszke, A., Gross, S., Massa, F., Lerer, A., Bradbury, J., Chanan, G., Killeen, T., Lin, Z., Gimelshein, N., Antiga, L. et\u00a0al. (2019). Pytorch: An imperative style, high-performance deep learning library. In Advances in Neural Information Processing Systems, 32, 8026\u20138037."},{"key":"2337_CR32","doi-asserted-by":"crossref","unstructured":"Peng, R., Wang, R., Wang, Z., Lai, Y., Wang, R. (2022). 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.","DOI":"10.1109\/CVPR52688.2022.00845"},{"issue":"2","key":"2337_CR33","doi-asserted-by":"publisher","first-page":"969","DOI":"10.1109\/TPAMI.2020.3020800","volume":"44","author":"X Qi","year":"2020","unstructured":"Qi, X., Liu, Z., Liao, R., Torr, P. H. S., Urtasun, R., & Jia, J. (2020). Geonet++: Iterative geometric neural network with edge-aware refinement for joint depth and surface normal estimation. IEEE Transactions on Pattern Analysis and Machine Intelligence, 44(2), 969\u2013984.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"2337_CR34","doi-asserted-by":"crossref","unstructured":"Ronneberger, O., Fischer, P., Brox, T. (2015). U-net: Convolutional networks for biomedical image segmentation. In International Conference on Medical Image Computing and Computer-Assisted Intervention, pp. 234\u2013241. Springer.","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"2337_CR35","doi-asserted-by":"crossref","unstructured":"Rossi, M., Gheche, M. E, Kuhn, A., Frossard, P. (2020). Joint graph-based depth refinement and normal estimation. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 12154\u201312163.","DOI":"10.1109\/CVPR42600.2020.01217"},{"key":"2337_CR36","doi-asserted-by":"crossref","unstructured":"Sch\u00f6nberger, J. L., Zheng, E., Frahm, J. M., Pollefeys, M. (2016). Pixelwise view selection for unstructured multi-view stereo. In Proceedings of the European Conference on Computer Vision, pp. 501\u2013518. Springer.","DOI":"10.1007\/978-3-319-46487-9_31"},{"key":"2337_CR37","doi-asserted-by":"crossref","unstructured":"Sch\u00f6ps, T., Sch\u00f6nberger, J.\u00a0L., Galliani, S., Sattler, T., Schindler, K., Pollefeys, M., Geiger, A. (2017). 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. 2538\u20132547.","DOI":"10.1109\/CVPR.2017.272"},{"key":"2337_CR38","doi-asserted-by":"crossref","unstructured":"Shi, Y., Xi, J., Hu, D., Cai, Z., Xu, K. (2023). Raymvsnet++: learning ray-based 1d implicit fields for accurate multi-view stereo. IEEE Transactions on Pattern Analysis and Machine Intelligence, 45(11), 13666\u201313682.","DOI":"10.1109\/TPAMI.2023.3296163"},{"key":"2337_CR39","doi-asserted-by":"crossref","unstructured":"Silberman, N., Hoiem, D., Kohli, P., Fergus, R. (2012). Indoor segmentation and support inference from rgbd images. In European Conference on Computer Vision, pp. 746\u2013760. Springer.","DOI":"10.1007\/978-3-642-33715-4_54"},{"issue":"4","key":"2337_CR40","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. (2020). Edgestereo: An effective multi-task learning network for stereo matching and edge detection. International Journal of Computer Vision, 128(4), 910\u2013930.","journal-title":"International Journal of Computer Vision"},{"key":"2337_CR41","doi-asserted-by":"crossref","unstructured":"Su, H., Jampani, V., Sun, D., Gallo, O., Learned-Miller, E., Kautz, J. (2019). Pixel-adaptive convolutional neural networks. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11166\u201311175.","DOI":"10.1109\/CVPR.2019.01142"},{"key":"2337_CR42","doi-asserted-by":"crossref","unstructured":"Su, W., Zhang, C., Xu, Q., Tao, W. (2024). Psdf: Prior-driven neural implicit surface learning for multi-view reconstruction. IEEE Transactions on Visualization and Computer Graphics","DOI":"10.1109\/TVCG.2024.3444035"},{"key":"2337_CR43","doi-asserted-by":"crossref","unstructured":"Sun, J., Shen, Z., Wang, Y., Bao, H., Zhou, X. (2021). Loftr: Detector-free local feature matching with transformers. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 8922\u20138931.","DOI":"10.1109\/CVPR46437.2021.00881"},{"key":"2337_CR44","doi-asserted-by":"publisher","first-page":"2348","DOI":"10.1609\/aaai.v37i2.25330","volume":"37","author":"W Su","year":"2023","unstructured":"Su, W., & Tao, W. (2023). Efficient edge-preserving multi-view stereo network for depth estimation. Proceedings of the AAAI Conference on Artificial Intelligence, 37, 2348\u20132356.","journal-title":"Proceedings of the AAAI Conference on Artificial Intelligence"},{"key":"2337_CR45","doi-asserted-by":"crossref","unstructured":"Su, W., Xu, Q., & Tao, W. (2022). Uncertainty-guided multi-view stereo network for depth estimation. IEEE Transactions on Circuits and Systems for Video Technology, 32(11), 7796\u20137808.","DOI":"10.1109\/TCSVT.2022.3183836"},{"key":"2337_CR46","doi-asserted-by":"crossref","unstructured":"Teed, Z., Deng, J. (2020). Raft: Recurrent all-pairs field transforms for optical flow. In European Conference on Computer vision, pp. 402\u2013419. Springer.","DOI":"10.1007\/978-3-030-58536-5_24"},{"issue":"5","key":"2337_CR47","doi-asserted-by":"publisher","first-page":"903","DOI":"10.1007\/s00138-011-0346-8","volume":"23","author":"E Tola","year":"2012","unstructured":"Tola, E., Strecha, C., & Fua, P. (2012). Efficient large-scale multi-view stereo for ultra high-resolution image sets. Machine Vision and Applications, 23(5), 903\u2013920.","journal-title":"Machine Vision and Applications"},{"key":"2337_CR48","doi-asserted-by":"crossref","unstructured":"Tosi, F., Liao, Y., Schmitt, C., Geiger, A. (2021). Smd-nets: Stereo mixture density networks. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 8942\u20138952.","DOI":"10.1109\/CVPR46437.2021.00883"},{"key":"2337_CR49","first-page":"14278","volume":"33","author":"P Truong","year":"2020","unstructured":"Truong, P., Danelljan, M., Gool, L. V., & Timofte, R. (2020). Gocor: Bringing globally optimized correspondence volumes into your neural network. Advances in Neural Information Processing Systems, 33, 14278\u201314290.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"2337_CR50","unstructured":"Vaswani, A, Shazeer, N, Parmar, N, Uszkoreit, J, Jones, L, Gomez, AN., Kaiser, L., Polosukhin, I. (2017). Attention is all you need. Advances in neural information processing systems, 30"},{"key":"2337_CR51","doi-asserted-by":"crossref","unstructured":"Wang, F., Galliani, S., Vogel, C., Pollefeys, M. (2022a). Itermvs: Iterative probability estimation for efficient multi-view stereo. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 8606\u20138615.","DOI":"10.1109\/CVPR52688.2022.00841"},{"key":"2337_CR52","doi-asserted-by":"crossref","unstructured":"Wang, F., Galliani, S., Vogel, C., Speciale, P., Pollefeys, M. (2021). Patchmatchnet: Learned multi-view patchmatch stereo. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 14194\u201314203.","DOI":"10.1109\/CVPR46437.2021.01397"},{"key":"2337_CR53","doi-asserted-by":"crossref","unstructured":"Wang, L., Gong, Y., Ma, X., Wang, Q., Zhou, K., Chen, L. (2022b). Is-mvsnet: Importance sampling-based mvsnet. In European Conference on Computer Vision, pp. 668\u2013683. Springer.","DOI":"10.1007\/978-3-031-19824-3_39"},{"key":"2337_CR54","doi-asserted-by":"crossref","unstructured":"Wang, S., Li, B., Dai, Y. (2022c). 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.","DOI":"10.1109\/CVPR52688.2022.00846"},{"key":"2337_CR55","doi-asserted-by":"crossref","unstructured":"Wang, Y., Zeng, Z., Guan, T., Yang, W., Chen, Z., Liu, W., Xu, L., Luo, Y. (2023). Adaptive patch deformation for textureless-resilient multi-view stereo. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 1621\u20131630.","DOI":"10.1109\/CVPR52729.2023.00162"},{"key":"2337_CR56","doi-asserted-by":"crossref","unstructured":"Wang, X., Zhu, Z., Huang, G., Qin, F., Ye, Y., He, Y., Chi, X., Wang, X. (2022d). Mvster: Epipolar transformer for efficient multi-view stereo. In European Conference on Computer Vision, pp. 573\u2013591. Springer.","DOI":"10.1007\/978-3-031-19821-2_33"},{"key":"2337_CR57","doi-asserted-by":"crossref","unstructured":"Wei, Z., Zhu, Q., Min, C., Chen, Y., Wang, G. (2021). Aa-rmvsnet: Adaptive aggregation recurrent multi-view stereo network. In Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 6187\u20136196.","DOI":"10.1109\/ICCV48922.2021.00613"},{"key":"2337_CR58","doi-asserted-by":"crossref","unstructured":"Woo, S., Park, J., Lee, J-Y, Kweon, I.\u00a0S. (2018). Cbam: Convolutional block attention module. In Proceedings of the European conference on computer vision (ECCV), pp. 3\u201319.","DOI":"10.1007\/978-3-030-01234-2_1"},{"key":"2337_CR59","doi-asserted-by":"crossref","unstructured":"Wu, D., Zhu, D., Zhang, G., Shi, W., Zhang, X., Li, J. (2022). J-rr: Joint monocular depth estimation and semantic edge detection exploiting reciprocal relations. In 2022 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 715\u2013722. IEEE.","DOI":"10.1109\/IROS47612.2022.9981343"},{"key":"2337_CR60","doi-asserted-by":"crossref","unstructured":"Xi, J., Shi, Y., Wang, Y., Guo, Y., Xu, K. (2022). 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.","DOI":"10.1109\/CVPR52688.2022.00840"},{"key":"2337_CR61","doi-asserted-by":"crossref","unstructured":"Xu, Qingshan, Tao, Wenbing. (2020a). Learning inverse depth regression for multi-view stereo with correlation cost volume. In Proceedings of the AAAI Conference on Artificial Intelligence, pp. 12508\u201312515.","DOI":"10.1609\/aaai.v34i07.6939"},{"key":"2337_CR62","doi-asserted-by":"crossref","unstructured":"Xu, Q., Tao, W. (2019). Multi-scale geometric consistency guided multi-view stereo. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5483\u20135492.","DOI":"10.1109\/CVPR.2019.00563"},{"key":"2337_CR63","doi-asserted-by":"crossref","unstructured":"Xu, Q., Tao, W. (2020). Planar prior assisted patchmatch multi-view stereo. In Proceedings of the AAAI Conference on Artificial Intelligence, pp. 12516\u201312523.","DOI":"10.1609\/aaai.v34i07.6940"},{"key":"2337_CR64","doi-asserted-by":"crossref","unstructured":"Xu, Q. Kong, W., Tao, W., & Pollefeys, M. (2022). Multi-scale geometric consistency guided and planar prior assisted multi-view stereo. IEEE Transactions on Pattern Analysis and Machine Intelligence, 45(4), 4945\u20134963.","DOI":"10.1109\/TPAMI.2022.3200074"},{"key":"2337_CR65","doi-asserted-by":"crossref","unstructured":"Xu, G., Wang, X., Ding, X., Yang, X. (2023). Iterative geometry encoding volume for stereo matching. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 21919\u201321928.","DOI":"10.1109\/CVPR52729.2023.02099"},{"key":"2337_CR66","doi-asserted-by":"crossref","unstructured":"Xu, Q., Su, W., Qi, Y., Tao, W., & Pollefeys, M. (2022). Learning inverse depth regression for pixelwise visibility-aware multi-view stereo networks. International Journal of Computer Vision, 130, 2040\u20132059.","DOI":"10.1007\/s11263-022-01628-2"},{"key":"2337_CR67","doi-asserted-by":"crossref","unstructured":"Yan, J., Wei, Z., Yi, H., Ding, M., Zhang, R., Chen, Y., Wang, G., Tai, Y. W. (2020). Dense hybrid recurrent multi-view stereo net with dynamic consistency checking. In Proceedings of the European Conference on Computer Vision","DOI":"10.1007\/978-3-030-58548-8_39"},{"key":"2337_CR68","doi-asserted-by":"crossref","unstructured":"Yang, J., Alvarez, J. M., & Liu, M. (2022). Non-parametric depth distribution modelling based depth inference for multi-view stereo. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 8626\u20138634","DOI":"10.1109\/CVPR52688.2022.00843"},{"key":"2337_CR69","doi-asserted-by":"crossref","unstructured":"Yang, J., Mao, W., Alvarez, J. M., Liu, M. (2020). Cost volume pyramid based depth inference for multi-view stereo. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4877\u20134886.","DOI":"10.1109\/CVPR42600.2020.00493"},{"key":"2337_CR70","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2021.104336","volume":"117","author":"X Yang","year":"2022","unstructured":"Yang, X., Feng, Z., Zhao, Y., Zhang, G., & He, L. (2022). Edge supervision and multi-scale cost volume for stereo matching. Image and Vision Computing, 117, 104336.","journal-title":"Image and Vision Computing"},{"key":"2337_CR71","doi-asserted-by":"crossref","unstructured":"Yao, Y., Luo, Z., Li, S., Fang, T., Quan, L. (2018). Mvsnet: Depth inference for unstructured multi-view stereo. In Proceedings of the European Conference on Computer Vision, pp. 767\u2013783.","DOI":"10.1007\/978-3-030-01237-3_47"},{"key":"2337_CR72","doi-asserted-by":"crossref","unstructured":"Yao, Y., Luo, Z., Li, S., Shen, T., Fang, T., Quan, L. (2019). Recurrent mvsnet for high-resolution multi-view stereo depth inference. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5525\u20135534.","DOI":"10.1109\/CVPR.2019.00567"},{"key":"2337_CR73","doi-asserted-by":"crossref","unstructured":"Yao, Y., Luo, Z., Li, S., Zhang, J., Ren, Y., Zhou, L., Fang, T., Quan, L. (2020). 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.","DOI":"10.1109\/CVPR42600.2020.00186"},{"key":"2337_CR74","doi-asserted-by":"crossref","unstructured":"Ye, X., Zhao, W., Liu, T., Huang, Z., Cao, Z., Li, X. (2023). Constraining depth map geometry for multi-view stereo: A dual-depth approach with saddle-shaped depth cells. In Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 17661\u201317670.","DOI":"10.1109\/ICCV51070.2023.01619"},{"key":"2337_CR75","doi-asserted-by":"crossref","unstructured":"Yu, Z., Gao, S. (2020). Fast-mvsnet: Sparse-to-dense multi-view stereo with learned propagation and gauss-newton refinement. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 1949\u20131958.","DOI":"10.1109\/CVPR42600.2020.00202"},{"key":"2337_CR76","doi-asserted-by":"publisher","first-page":"6871","DOI":"10.1609\/aaai.v38i7.28512","volume":"38","author":"Z Yuan","year":"2024","unstructured":"Yuan, Z., Cao, J., Li, Z., Jiang, H., & Wang, Z. (2024). SD-MVS: Segmentation-driven deformation multi-view stereo with spherical refinement and EM optimization. Proceedings of the AAAI Conference on Artificial Intelligence, 38, 6871\u20136880.","journal-title":"Proceedings of the AAAI Conference on Artificial Intelligence"},{"key":"2337_CR77","doi-asserted-by":"crossref","unstructured":"Zhang, Z, Peng, R, Hu, Y, Wang, R. (2023). Geomvsnet: Learning multi-view stereo with geometry perception. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 21508\u201321518.","DOI":"10.1109\/CVPR52729.2023.02060"},{"issue":"1","key":"2337_CR78","doi-asserted-by":"publisher","first-page":"199","DOI":"10.1007\/s11263-022-01697-3","volume":"131","author":"J Zhang","year":"2023","unstructured":"Zhang, J., Li, S., Luo, Z., Fang, T., & Yao, Y. (2023). Vis-mvsnet: Visibility-aware multi-view stereo network. International Journal of Computer Vision, 131(1), 199\u2013214.","journal-title":"International Journal of Computer Vision"}],"container-title":["International Journal of Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-024-02337-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11263-024-02337-8\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-024-02337-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,10]],"date-time":"2025-05-10T06:53:12Z","timestamp":1746859992000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11263-024-02337-8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,1,7]]},"references-count":78,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2025,6]]}},"alternative-id":["2337"],"URL":"https:\/\/doi.org\/10.1007\/s11263-024-02337-8","relation":{},"ISSN":["0920-5691","1573-1405"],"issn-type":[{"value":"0920-5691","type":"print"},{"value":"1573-1405","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,1,7]]},"assertion":[{"value":"5 May 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"17 December 2024","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"7 January 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}