{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,25]],"date-time":"2025-10-25T10:30:39Z","timestamp":1761388239670,"version":"build-2065373602"},"reference-count":46,"publisher":"Springer Science and Business Media LLC","issue":"5","license":[{"start":{"date-parts":[[2025,8,21]],"date-time":"2025-08-21T00:00:00Z","timestamp":1755734400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,8,21]],"date-time":"2025-08-21T00:00:00Z","timestamp":1755734400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"name":"Key Laboratory of Intelligent Manufacturing and Industrial Internet Technology, Fujian Province","award":["ZZKY202203"],"award-info":[{"award-number":["ZZKY202203"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Multimedia Systems"],"published-print":{"date-parts":[[2025,10]]},"DOI":"10.1007\/s00530-025-01949-5","type":"journal-article","created":{"date-parts":[[2025,8,21]],"date-time":"2025-08-21T12:24:28Z","timestamp":1755779068000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["DA-MVSNet:depth-aware multi-view stereo network for 3D reconstruction"],"prefix":"10.1007","volume":"31","author":[{"given":"Xiaoyan","family":"Zhang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ling","family":"Luo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jingbo","family":"Xia","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiangfei","family":"Dai","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,8,21]]},"reference":[{"issue":"1\u20132","key":"1949_CR1","first-page":"1","volume":"9","author":"Y Furukawa","year":"2015","unstructured":"Furukawa, Y., Hern\u00e1ndez, C.: Multi-view stereo: a tutorial. Found. Trends\u00ae Comput. Graph. Vis. 9(1\u20132), 1\u2013148 (2015)","journal-title":"Found. Trends\u00ae Comput. Graph. Vis."},{"key":"1949_CR2","doi-asserted-by":"crossref","unstructured":"Sch\u00f6nberger, J.L., Zheng, E., Frahm, J.-M., Pollefeys, M.: Pixelwise view selection for unstructured multi-view stereo. In: Computer Vision\u2013ECCV 2016: 14th European Conference, Amsterdam, The Netherlands, October 11-14, 2016, Proceedings, Part III 14, pp. 501\u2013518 (2016). Springer","DOI":"10.1007\/978-3-319-46487-9_31"},{"key":"1949_CR3","doi-asserted-by":"publisher","unstructured":"Furukawa, Y., Ponce, J.: Accurate, dense, and robust multi-view stereopsis. In: 2007 IEEE Conference on Computer Vision and Pattern Recognition (2007). https:\/\/doi.org\/10.1109\/cvpr.2007.383246","DOI":"10.1109\/cvpr.2007.383246"},{"key":"1949_CR4","doi-asserted-by":"publisher","unstructured":"Ji, M., Gall, J., Zheng, H., Liu, Y., Fang, L.: Surfacenet: an end-to-end 3d neural network for multiview stereopsis. In: 2017 IEEE International Conference on Computer Vision (ICCV) (2017). https:\/\/doi.org\/10.1109\/iccv.2017.253","DOI":"10.1109\/iccv.2017.253"},{"key":"1949_CR5","doi-asserted-by":"publisher","unstructured":"Galliani, S., Lasinger, K., Schindler, K.: Massively parallel multiview stereopsis by surface normal diffusion. In: 2015 IEEE International Conference on Computer Vision (ICCV) (2015). https:\/\/doi.org\/10.1109\/iccv.2015.106","DOI":"10.1109\/iccv.2015.106"},{"key":"1949_CR6","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 (ECCV), pp. 767\u2013783 (2018)","DOI":"10.1007\/978-3-030-01237-3_47"},{"key":"1949_CR7","doi-asserted-by":"publisher","unstructured":"Chen, R., Han, S., Xu, J., Su, H.: Point-based multi-view stereo network. In: 2019 IEEE\/CVF International Conference on Computer Vision (ICCV) (2019). https:\/\/doi.org\/10.1109\/iccv.2019.00162","DOI":"10.1109\/iccv.2019.00162"},{"key":"1949_CR8","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: 2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2019). https:\/\/doi.org\/10.1109\/cvpr.2019.00567","DOI":"10.1109\/cvpr.2019.00567"},{"key":"1949_CR9","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: 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2020). https:\/\/doi.org\/10.1109\/cvpr42600.2020.00257","DOI":"10.1109\/cvpr42600.2020.00257"},{"key":"1949_CR10","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2021.3082562","author":"J Yang","year":"2021","unstructured":"Yang, J., Mao, W., Alvarez, J., Liu, M.: Cost volume pyramid based depth inference for multi-view stereo. IEEE Trans. Pattern Anal. Mach. Intell. (2021). https:\/\/doi.org\/10.1109\/tpami.2021.3082562","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"1949_CR11","doi-asserted-by":"publisher","unstructured":"Lin, T.-Y., Dollar, P., Girshick, R., He, K., Hariharan, B., Belongie, S.: Feature pyramid networks for object detection. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2017). https:\/\/doi.org\/10.1109\/cvpr.2017.106","DOI":"10.1109\/cvpr.2017.106"},{"key":"1949_CR12","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":"1949_CR13","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2019.2913372","author":"J Hu","year":"2020","unstructured":"Hu, J., Shen, L., Albanie, S., Sun, G., Wu, E.: Squeeze-and-excitation networks. IEEE Trans. Pattern Anal. Mach. Intell. (2020). https:\/\/doi.org\/10.1109\/tpami.2019.2913372","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"1949_CR14","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A., Kaiser, L., Polosukhin, I.: Attention is all you need. Neural Information Processing Systems, Neural Information Processing Systems (2017)"},{"key":"1949_CR15","doi-asserted-by":"publisher","unstructured":"Luo, K., Guan, T., Ju, L., Huang, H., Luo, Y.: P-mvsnet: learning patch-wise matching confidence aggregation for multi-view stereo. In: 2019 IEEE\/CVF International Conference on Computer Vision (ICCV) (2019). https:\/\/doi.org\/10.1109\/iccv.2019.01055","DOI":"10.1109\/iccv.2019.01055"},{"key":"1949_CR16","doi-asserted-by":"publisher","unstructured":"Wei, Z., Zhu, Q., Min, C., Chen, Y., Wang, G.: Aa-rmvsnet: adaptive aggregation recurrent multi-view stereo network. In: 2021 IEEE\/CVF International Conference on Computer Vision (ICCV) (2021). https:\/\/doi.org\/10.1109\/iccv48922.2021.00613","DOI":"10.1109\/iccv48922.2021.00613"},{"key":"1949_CR17","doi-asserted-by":"publisher","unstructured":"Wang, F., Galliani, S., Vogel, C., Pollefeys, M.: Itermvs: iterative probability estimation for efficient multi-view stereo. In: 2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2022). https:\/\/doi.org\/10.1109\/cvpr52688.2022.00841","DOI":"10.1109\/cvpr52688.2022.00841"},{"key":"1949_CR18","doi-asserted-by":"publisher","unstructured":"Wang, F., Galliani, S., Vogel, C., Speciale, P., Pollefeys, M.: Patchmatchnet: learned multi-view patchmatch stereo. In: 2021 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2021). https:\/\/doi.org\/10.1109\/cvpr46437.2021.01397","DOI":"10.1109\/cvpr46437.2021.01397"},{"key":"1949_CR19","doi-asserted-by":"crossref","unstructured":"Dai, Y., Zhu, Z., Rao, Z., Li, B.: Mvs2: Deep unsupervised multi-view stereo with multi-view symmetry. In: 2019 International Conference on 3D Vision (3DV), pp. 1\u20138 (2019). IEEE","DOI":"10.1109\/3DV.2019.00010"},{"key":"1949_CR20","doi-asserted-by":"crossref","unstructured":"Yan, Z., Wang, K., Li, X., Zhang, Z., Li, J., Yang, J.: Desnet: Decomposed scale-consistent network for unsupervised depth completion. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 37, pp. 3109\u20133117 (2023)","DOI":"10.1609\/aaai.v37i3.25415"},{"key":"1949_CR21","doi-asserted-by":"crossref","unstructured":"Huang, B., Yi, H., Huang, C., He, Y., Liu, J., Liu, X.: M3vsnet: unsupervised multi-metric multi-view stereo network. In: 2021 IEEE International Conference on Image Processing (ICIP), pp. 3163\u20133167 (2021). IEEE","DOI":"10.1109\/ICIP42928.2021.9506469"},{"key":"1949_CR22","doi-asserted-by":"crossref","unstructured":"Yang, J., Alvarez, J.M., Liu, M.: Self-supervised learning of depth inference for multi-view stereo. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 7526\u20137534 (2021)","DOI":"10.1109\/CVPR42600.2020.00493"},{"key":"1949_CR23","doi-asserted-by":"crossref","unstructured":"Wang, K., Zhang, Z., Yan, Z., Li, X., Xu, B., Li, J., Yang, J.: Regularizing nighttime weirdness: efficient self-supervised monocular depth estimation in the dark. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 16055\u201316064 (2021)","DOI":"10.1109\/ICCV48922.2021.01575"},{"key":"1949_CR24","doi-asserted-by":"crossref","unstructured":"Xu, H., Zhou, Z., Wang, Y., Kang, W., Sun, B., Li, H., Qiao, Y.: Digging into uncertainty in self-supervised multi-view stereo. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 6078\u20136087 (2021)","DOI":"10.1109\/ICCV48922.2021.00602"},{"key":"1949_CR25","doi-asserted-by":"publisher","unstructured":"Dai, J., Qi, H., Xiong, Y., Li, Y., Zhang, G., Hu, H., Wei, Y.: Deformable convolutional networks. In: 2017 IEEE International Conference on Computer Vision (ICCV) (2017). https:\/\/doi.org\/10.1109\/iccv.2017.89","DOI":"10.1109\/iccv.2017.89"},{"key":"1949_CR26","doi-asserted-by":"crossref","unstructured":"Wang, Y., Guan, T., Chen, Z., Luo, Y., Luo, K., Ju, L.: Mesh-guided multi-view stereo with pyramid architecture. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2039\u20132048 (2020)","DOI":"10.1109\/CVPR42600.2020.00211"},{"key":"1949_CR27","unstructured":"Chen, L.-C., Papandreou, G., Schroff, F., Adam, H.: Rethinking atrous convolution for semantic image segmentation. arXiv: Computer Vision and Pattern Recognition, arXiv: Computer Vision and Pattern Recognition (2017)"},{"issue":"1","key":"1949_CR28","doi-asserted-by":"publisher","first-page":"6766","DOI":"10.1038\/s41598-024-55612-6","volume":"14","author":"R Jia","year":"2024","unstructured":"Jia, R., Yu, J., Hu, Z., Yuan, F.: Bsi-mvs: multi-view stereo network with bidirectional semantic information. Sci. Rep. 14(1), 6766 (2024)","journal-title":"Sci. Rep."},{"key":"1949_CR29","doi-asserted-by":"publisher","unstructured":"Luo, K., Guan, T., Ju, L., Wang, Y., Chen, Z., Luo, Y.: Attention-aware multi-view stereo. In: 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2020). https:\/\/doi.org\/10.1109\/cvpr42600.2020.00166","DOI":"10.1109\/cvpr42600.2020.00166"},{"key":"1949_CR30","doi-asserted-by":"publisher","unstructured":"Zhang, X., Hu, Y., Wang, H., Cao, X., Zhang, B.: Long-range attention network for multi-view stereo. In: 2021 IEEE Winter Conference on Applications of Computer Vision (WACV) (2021). https:\/\/doi.org\/10.1109\/wacv48630.2021.00383","DOI":"10.1109\/wacv48630.2021.00383"},{"key":"1949_CR31","doi-asserted-by":"crossref","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). Springer","DOI":"10.1007\/978-3-031-19821-2_33"},{"issue":"1","key":"1949_CR32","doi-asserted-by":"publisher","first-page":"377","DOI":"10.1007\/s00530-022-01009-2","volume":"29","author":"W Liu","year":"2023","unstructured":"Liu, W., Wang, J., Qu, H., Shen, L.: Hierarchical mvsnet with cost volume separation and fusion based on u-shape feature extraction. Multimed. Syst. 29(1), 377\u2013387 (2023)","journal-title":"Multimed. Syst."},{"key":"1949_CR33","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2023.109819","author":"G Xu","year":"2023","unstructured":"Xu, G., Liao, W., Zhang, X., Li, C., He, X., Wu, X.: Haar wavelet downsampling: a simple but effective downsampling module for semantic segmentation. Pattern Recogn. (2023). https:\/\/doi.org\/10.1016\/j.patcog.2023.109819","journal-title":"Pattern Recogn."},{"key":"1949_CR34","doi-asserted-by":"publisher","unstructured":"Hu, M., Wang, S., Li, B., Ning, S., Fan, L., Gong, X.: Penet: towards precise and efficient image guided depth completion. In: 2021 IEEE International Conference on Robotics and Automation (ICRA) (2021). https:\/\/doi.org\/10.1109\/icra48506.2021.9561035","DOI":"10.1109\/icra48506.2021.9561035"},{"key":"1949_CR35","doi-asserted-by":"publisher","DOI":"10.3390\/s21165476","author":"R Wang","year":"2021","unstructured":"Wang, R., Zou, J., Wen, J.Z.: Sfa-mden: semantic-feature-aided monocular depth estimation network using dual branches. Sensors (2021). https:\/\/doi.org\/10.3390\/s21165476","journal-title":"Sensors"},{"key":"1949_CR36","doi-asserted-by":"crossref","unstructured":"Yan, Z., Wang, K., Li, X., Zhang, Z., Li, J., Yang, J.: Rignet: Repetitive image guided network for depth completion. In: European Conference on Computer Vision, pp. 214\u2013230 (2022). Springer","DOI":"10.1007\/978-3-031-19812-0_13"},{"key":"1949_CR37","unstructured":"Wang, K., Yan, Z., Fan, J., Li, J., Yang, J.: Learning inverse laplacian pyramid for progressive depth completion. arXiv preprint arXiv:2502.07289 (2025)"},{"key":"1949_CR38","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"1949_CR39","doi-asserted-by":"publisher","unstructured":"Collins, R.T.: A space-sweep approach to true multi-image matching. In: Proceedings CVPR IEEE Computer Society Conference on Computer Vision and Pattern Recognition (1996). https:\/\/doi.org\/10.1109\/cvpr.1996.517097","DOI":"10.1109\/cvpr.1996.517097"},{"key":"1949_CR40","doi-asserted-by":"publisher","unstructured":"Jensen, R., Dahl, A., Vogiatzis, G., Tola, E., Aanaes, H.: Large scale multi-view stereopsis evaluation. In: 2014 IEEE Conference on Computer Vision and Pattern Recognition (2014). https:\/\/doi.org\/10.1109\/cvpr.2014.59","DOI":"10.1109\/cvpr.2014.59"},{"key":"1949_CR41","doi-asserted-by":"publisher","unstructured":"Yao, Y., Luo, Z., Li, S., Zhang, J., Ren, Y., Zhou, L., Fang, T., Quan, L.: Blendedmvs: a large-scale dataset for generalized multi-view stereo networks. In: 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2020). https:\/\/doi.org\/10.1109\/cvpr42600.2020.00186","DOI":"10.1109\/cvpr42600.2020.00186"},{"key":"1949_CR42","doi-asserted-by":"publisher","DOI":"10.1145\/3072959.3073599","author":"A Knapitsch","year":"2017","unstructured":"Knapitsch, A., Park, J., Zhou, Q.-Y., Koltun, V.: Tanks and temples. ACM Trans. Graph. (2017). https:\/\/doi.org\/10.1145\/3072959.3073599","journal-title":"ACM Trans. Graph."},{"key":"1949_CR43","unstructured":"Zhou, Q.-Y., Park, J., Koltun, V.: Open3d: a modern library for 3d data processing. arXiv: Computer Vision and Pattern Recognition, arXiv: Computer Vision and Pattern Recognition (2018)"},{"key":"1949_CR44","doi-asserted-by":"crossref","unstructured":"Yan, J., Wei, Z., Yi, H., Ding, M., Zhang, R., Chen, Y., Wang, G., Tai, Y.-W.: Dense hybrid recurrent multi-view stereo net with dynamic consistency checking. In: European Conference on Computer Vision, pp. 674\u2013689 (2020). Springer","DOI":"10.1007\/978-3-030-58548-8_39"},{"key":"1949_CR45","doi-asserted-by":"publisher","unstructured":"Schonberger, J.L., Frahm, J.-M.: Structure-from-motion revisited. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2016). https:\/\/doi.org\/10.1109\/cvpr.2016.445","DOI":"10.1109\/cvpr.2016.445"},{"key":"1949_CR46","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"}],"container-title":["Multimedia Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00530-025-01949-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00530-025-01949-5\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00530-025-01949-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,25]],"date-time":"2025-10-25T10:26:28Z","timestamp":1761387988000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00530-025-01949-5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8,21]]},"references-count":46,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2025,10]]}},"alternative-id":["1949"],"URL":"https:\/\/doi.org\/10.1007\/s00530-025-01949-5","relation":{},"ISSN":["0942-4962","1432-1882"],"issn-type":[{"type":"print","value":"0942-4962"},{"type":"electronic","value":"1432-1882"}],"subject":[],"published":{"date-parts":[[2025,8,21]]},"assertion":[{"value":"10 February 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"17 July 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"21 August 2025","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"}},{"value":"Not applicable.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethical approval"}},{"value":"All authors have read and approved the final manuscript.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent for publication"}}],"article-number":"368"}}