{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T12:48:51Z","timestamp":1772801331259,"version":"3.50.1"},"reference-count":51,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100002855","name":"Ministry of Science and Technology of the People's Republic of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100002855","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2023YFC3010402"],"award-info":[{"award-number":["2023YFC3010402"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Expert Systems with Applications"],"published-print":{"date-parts":[[2026,1]]},"DOI":"10.1016\/j.eswa.2025.129177","type":"journal-article","created":{"date-parts":[[2025,7,27]],"date-time":"2025-07-27T21:54:18Z","timestamp":1753653258000},"page":"129177","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"PD","title":["Super resolution enhanced multi-view stereo network based on Gumbel sampling"],"prefix":"10.1016","volume":"296","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-7770-6303","authenticated-orcid":false,"given":"Shichao","family":"Wang","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3876-1804","authenticated-orcid":false,"given":"Mingxing","family":"Jia","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0009-0004-2948-6304","authenticated-orcid":false,"given":"Shijie","family":"Chang","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1030-2593","authenticated-orcid":false,"given":"Dapeng","family":"Niu","sequence":"additional","affiliation":[]}],"member":"78","reference":[{"key":"10.1016\/j.eswa.2025.129177_bib0001","doi-asserted-by":"crossref","first-page":"153","DOI":"10.1007\/s11263-016-0902-9","article-title":"Large-scale data for multiple-view stereopsis","volume":"120","author":"Aan\u00e6s","year":"2016","journal-title":"International Journal of Computer Vision"},{"key":"10.1016\/j.eswa.2025.129177_bib0002","unstructured":"Cao, C., Ren, X., & Fu, Y. (2024). MVSFormer++: Revealing the Devil in transformer\u2019s details for multi-view stereo. arXiv preprint arXiv:2401.11673."},{"key":"10.1016\/j.eswa.2025.129177_bib0003","series-title":"2019 IEEE\/CVF International conference on computer vision (ICCV)","first-page":"1538","article-title":"Point-based multi-view stereo network","author":"Chen","year":"2019"},{"key":"10.1016\/j.eswa.2025.129177_bib0004","first-page":"2521","article-title":"Deep stereo using adaptive thin volume representation with uncertainty awareness","author":"Cheng","year":"2019","journal-title":"2020 IEEE\/CVF Conference on computer vision and pattern Rrecognition (CVPR)"},{"key":"10.1016\/j.eswa.2025.129177_bib0005","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"2524","article-title":"Deep stereo using adaptive thin volume representation with uncertainty awareness","author":"Cheng","year":"2020"},{"key":"10.1016\/j.eswa.2025.129177_bib0006","first-page":"8575","article-title":"TransMVSNet: Global context-aware multi-view stereo network with transformers","author":"Ding","year":"2021","journal-title":"2022 IEEE\/CVF Conference on computer vision and pattern recognition (CVPR)"},{"key":"10.1016\/j.eswa.2025.129177_bib0007","doi-asserted-by":"crossref","first-page":"1362","DOI":"10.1109\/TPAMI.2009.161","article-title":"Accurate, dense, and robust multiview stereopsis","volume":"32","author":"Furukawa","year":"2010","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"10.1016\/j.eswa.2025.129177_bib0008","doi-asserted-by":"crossref","first-page":"873","DOI":"10.1109\/ICCV.2015.106","article-title":"Massively parallel multiview stereopsis by surface normal diffusion","author":"Galliani","year":"2015","journal-title":"2015 IEEE International conference on computer vision (ICCV)"},{"key":"10.1016\/j.eswa.2025.129177_bib0009","first-page":"2492","article-title":"Cascade cost volume for high-resolution multi-view stereo and stereo matching","author":"Gu","year":"2019","journal-title":"2020 IEEE\/CVF Conference on computer vision and pattern recognition (CVPR)"},{"key":"10.1016\/j.eswa.2025.129177_bib0010","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2025.111456","article-title":"ICV-Net: An identity cost volume network for multi-view stereo depth inference","volume":"162","author":"He","year":"2025","journal-title":"Pattern Recognition"},{"key":"10.1016\/j.eswa.2025.129177_bib0011","series-title":"2021 IEEE International conference on image processing (ICIP)","first-page":"3163","article-title":"M3VSNet: Unsupervised multi-metric multi-view stereo network","author":"Huang","year":"2021"},{"key":"10.1016\/j.eswa.2025.129177_bib0012","unstructured":"Jang, E., Gu, S. S., & Poole, B. (2016). Categorical reparameterization with gumbel-softmax. arxiv:1611.01144."},{"key":"10.1016\/j.eswa.2025.129177_bib0013","doi-asserted-by":"crossref","first-page":"2326","DOI":"10.1109\/ICCV.2017.253","article-title":"SurfaceNet: An end-to-end 3D neural network for multiview stereopsis","author":"Ji","year":"2017","journal-title":"2017 IEEE International conference on computer vision (ICCV)"},{"key":"10.1016\/j.eswa.2025.129177_bib0014","unstructured":"Kar, A., H\u00e4ne, C., & Malik, J. (2017). Learning a multi-view stereo machine. arXiv:1708.05375."},{"key":"10.1016\/j.eswa.2025.129177_bib0015","unstructured":"Khot, T., Agrawal, S., Tulsiani, S., Mertz, C., Lucey, S., & Hebert, M. (2019). Learning unsupervised multi-view stereopsis via robust photometric consistency. arXiv preprint arXiv:1905.02706."},{"key":"10.1016\/j.eswa.2025.129177_bib0016","unstructured":"Kingma, D. P., Mohamed, S., Rezende, D. J., & Welling, M. (2014). Semi-supervised learning with deep generative models. arXiv:1406.5298."},{"key":"10.1016\/j.eswa.2025.129177_bib0017","doi-asserted-by":"crossref","first-page":"418","DOI":"10.1109\/TPAMI.2005.44","article-title":"A quasi-dense approach to surface reconstruction from uncalibrated images","volume":"27","author":"Lhuillier","year":"2005","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"10.1016\/j.eswa.2025.129177_bib0018","unstructured":"Li, J., Chen, T., Shi, R., Lou, Y., Li, Y.-L., & Lu, C. (2021). Localization with sampling-argmax. arXiv:2110.08825."},{"key":"10.1016\/j.eswa.2025.129177_bib0019","first-page":"11627","article-title":"Generalized focal loss V2: Learning reliable localization quality estimation for dense object detection","author":"Li","year":"2020","journal-title":"2021 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)"},{"key":"10.1016\/j.eswa.2025.129177_bib0020","first-page":"8564","article-title":"WT-MVSNet: window-based transformers for multi-view stereo","volume":"35","author":"Liao","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.eswa.2025.129177_bib0021","doi-asserted-by":"crossref","first-page":"1132","DOI":"10.1109\/CVPRW.2017.151","article-title":"Enhanced deep residual networks for single image super-resolution","author":"Lim","year":"2017","journal-title":"2017 IEEE Conference on computer vision and pattern recognition workshops (CVPRW)"},{"issue":"8","key":"10.1016\/j.eswa.2025.129177_bib0022","doi-asserted-by":"crossref","first-page":"7401","DOI":"10.1109\/TCSVT.2024.3376692","article-title":"Geometry-enhanced attentive multi-view stereo for challenging matching scenarios","volume":"34","author":"Liu","year":"2024","journal-title":"IEEE Transactions on Circuits and Systems for Video Technology"},{"key":"10.1016\/j.eswa.2025.129177_bib0023","doi-asserted-by":"crossref","DOI":"10.1016\/j.dsp.2024.104496","article-title":"Self-supervised monocular depth estimation on water scenes via specular reflection prior","volume":"149","author":"Lu","year":"2024","journal-title":"Digital Signal Processing"},{"key":"10.1016\/j.eswa.2025.129177_bib0024","doi-asserted-by":"crossref","first-page":"10451","DOI":"10.1109\/ICCV.2019.01055","article-title":"P-MVSNet: Learning patch-wise matching confidence aggregation for multi-view stereo","author":"Luo","year":"2019","journal-title":"2019 IEEE\/CVF International conference on computer vision (ICCV)"},{"key":"10.1016\/j.eswa.2025.129177_bib0025","doi-asserted-by":"crossref","first-page":"5712","DOI":"10.1109\/ICCV48922.2021.00568","article-title":"EPP-MVSNet: Epipolar-assembling based depth prediction for multi-view stereo","author":"Ma","year":"2021","journal-title":"2021 IEEE\/CVF International conference on computer vision (ICCV)"},{"key":"10.1016\/j.eswa.2025.129177_bib0026","doi-asserted-by":"crossref","unstructured":"Ma, Z., Teed, Z., & Deng, J. (2022). Multiview stereo with cascaded epipolar RAFT. arXiv:2205.04502.","DOI":"10.1007\/978-3-031-19821-2_42"},{"key":"10.1016\/j.eswa.2025.129177_bib0027","series-title":"2022 IEEE\/CVF Conference on computer vision and pattern recognition (CVPR)","first-page":"12981","article-title":"Generalized binary search network for highly-efficient multi-view stereo","author":"Mi","year":"2022"},{"key":"10.1016\/j.eswa.2025.129177_bib0028","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"8645","article-title":"Rethinking depth estimation for multi-view stereo: A unified representation","author":"Peng","year":"2022"},{"key":"10.1016\/j.eswa.2025.129177_bib0029","doi-asserted-by":"crossref","first-page":"4104","DOI":"10.1109\/CVPR.2016.445","article-title":"Structure-from-motion revisited","author":"Sch\u00f6nberger","year":"2016","journal-title":"2016 IEEE Conference on computer vision and pattern recognition (CVPR)"},{"key":"10.1016\/j.eswa.2025.129177_bib0030","doi-asserted-by":"crossref","DOI":"10.1016\/j.inffus.2024.102399","article-title":"Large-scale aerial scene perception based on self-supervised multi-view stereo via cycled generative adversarial network","volume":"109","author":"Tong","year":"2024","journal-title":"Information Fusion"},{"key":"10.1016\/j.eswa.2025.129177_bib0031","article-title":"The application of deep learning in stereo matching and disparity estimation: A bibliometric review","volume":"238","author":"Wang","year":"2024","journal-title":"Expert Systems with Applications"},{"key":"10.1016\/j.eswa.2025.129177_bib0032","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"8606","article-title":"IterMVS: Iterative probability estimation for efficient multi-view stereo","author":"Wang","year":"2022"},{"key":"10.1016\/j.eswa.2025.129177_bib0033","doi-asserted-by":"crossref","first-page":"113911","DOI":"10.1016\/j.knosys.2025.113911","article-title":"Generalized deep aerial multi-view stereo network based on gradient balance masked representation learning","volume":"325","author":"Wang","year":"2025","journal-title":"Knowledge-Based Systems"},{"issue":"6","key":"10.1016\/j.eswa.2025.129177_bib0034","doi-asserted-by":"crossref","DOI":"10.1088\/1361-6501\/adde7b","article-title":"ADLE: adaptive distribution likelihood estimation for stereo matching","volume":"36","author":"Wang","year":"2025","journal-title":"Measurement Science and Technology"},{"key":"10.1016\/j.eswa.2025.129177_bib0035","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"8655","article-title":"Efficient multi-view stereo by iterative dynamic cost volume","author":"Wang","year":"2022"},{"key":"10.1016\/j.eswa.2025.129177_bib0036","series-title":"European conference on computer vision","first-page":"573","article-title":"MVSTER: Epipolar transformer for efficient multi-view stereo","author":"Wang","year":"2022"},{"key":"10.1016\/j.eswa.2025.129177_bib0037","doi-asserted-by":"crossref","first-page":"6167","DOI":"10.1109\/ICCV48922.2021.00613","article-title":"AA-RMVSNet: Adaptive aggregation recurrent multi-view stereo network","author":"Wei","year":"2021","journal-title":"2021 IEEE\/CVF International Conference on Computer Vision (ICCV)"},{"key":"10.1016\/j.eswa.2025.129177_bib0038","doi-asserted-by":"crossref","unstructured":"Woodford, O. J., & Rosten, E. (2020). Large scale photometric bundle adjustment. arXiv:2008.11762.","DOI":"10.5244\/C.34.177"},{"key":"10.1016\/j.eswa.2025.129177_bib0039","doi-asserted-by":"crossref","first-page":"8585","DOI":"10.1109\/CVPR52688.2022.00840","article-title":"RayMVSNet: Learning ray-based 1d implicit fields for accurate multi-view stereo","author":"Xi","year":"2022","journal-title":"2022 IEEE\/CVF Conference on computer vision and pattern recognition (CVPR)"},{"key":"10.1016\/j.eswa.2025.129177_bib0040","series-title":"Proceedings of the IEEE\/CVF international conference on computer vision","first-page":"6078","article-title":"Digging into uncertainty in self-supervised multi-view stereo","author":"Xu","year":"2021"},{"key":"10.1016\/j.eswa.2025.129177_bib0041","doi-asserted-by":"crossref","first-page":"5478","DOI":"10.1109\/CVPR.2019.00563","article-title":"Multi-scale geometric consistency guided multi-view stereo","author":"Xu","year":"2019","journal-title":"2019 IEEE\/CVF Conference on computer vision and pattern recognition (CVPR)"},{"key":"10.1016\/j.eswa.2025.129177_bib0042","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. arXiv:2007.10872.","DOI":"10.1007\/978-3-030-58548-8_39"},{"key":"10.1016\/j.eswa.2025.129177_bib0043","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2023.120730","article-title":"Extracting cow point clouds from multi-view RGB images with an improved YOLACT++ instance segmentation","volume":"230","author":"Yang","year":"2023","journal-title":"Expert Systems with Applications"},{"key":"10.1016\/j.eswa.2025.129177_bib0044","first-page":"4876","article-title":"Cost volume pyramid based depth inference for multi-view stereo","author":"Yang","year":"2019","journal-title":"2020 IEEE\/CVF Conference on computer vision and pattern recognition (CVPR)"},{"key":"10.1016\/j.eswa.2025.129177_bib0045","series-title":"European conference on computer vision","article-title":"MVSNet: Depth inference for unstructured multi-view stereo","author":"Yao","year":"2018"},{"key":"10.1016\/j.eswa.2025.129177_bib0046","doi-asserted-by":"crossref","first-page":"5520","DOI":"10.1109\/CVPR.2019.00567","article-title":"Recurrent MVSNet for high-resolution multi-view stereo depth inference","author":"Yao","year":"2019","journal-title":"2019 IEEE\/CVF Conference on computer vision and pattern recognition (CVPR)"},{"key":"10.1016\/j.eswa.2025.129177_bib0047","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"1790","article-title":"BlendedMVS: A large-scale dataset for generalized multi-view stereo networks","author":"Yao","year":"2020"},{"key":"10.1016\/j.eswa.2025.129177_bib0048","series-title":"Computer vision\u2013ECCV 2020: 16th European conference, Glasgow, UK, August 23\u201328, 2020, proceedings, Part IX 16","first-page":"766","article-title":"Pyramid multi-view stereo net with self-adaptive view aggregation","author":"Yi","year":"2020"},{"key":"10.1016\/j.eswa.2025.129177_bib0049","doi-asserted-by":"crossref","DOI":"10.1016\/j.dsp.2022.103514","article-title":"A survey of modern deep learning based object detection models","volume":"126","author":"Zaidi","year":"2022","journal-title":"Digital Signal Processing"},{"key":"10.1016\/j.eswa.2025.129177_bib0050","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"21508","article-title":"GeoMVSNet: Learning multi-view stereo with geometry perception","author":"Zhang","year":"2023"},{"issue":"11","key":"10.1016\/j.eswa.2025.129177_bib0051","doi-asserted-by":"crossref","first-page":"10732","DOI":"10.1109\/TCSVT.2024.3416474","article-title":"Self-constructing stereo correspondences for unsupervised multi-view stereo","volume":"34","author":"Zhu","year":"2024","journal-title":"IEEE Transactions on Circuits and Systems for Video Technology"}],"container-title":["Expert Systems with Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0957417425027939?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0957417425027939?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T09:45:18Z","timestamp":1772790318000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0957417425027939"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1]]},"references-count":51,"alternative-id":["S0957417425027939"],"URL":"https:\/\/doi.org\/10.1016\/j.eswa.2025.129177","relation":{},"ISSN":["0957-4174"],"issn-type":[{"value":"0957-4174","type":"print"}],"subject":[],"published":{"date-parts":[[2026,1]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Super resolution enhanced multi-view stereo network based on Gumbel sampling","name":"articletitle","label":"Article Title"},{"value":"Expert Systems with Applications","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.eswa.2025.129177","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2025 Elsevier Ltd. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"129177"}}