{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,17]],"date-time":"2026-08-17T19:37:32Z","timestamp":1786995452691,"version":"build-2736575974"},"reference-count":40,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/2.zoppoz.workers.dev:443\/https\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/2.zoppoz.workers.dev:443\/https\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/2.zoppoz.workers.dev:443\/https\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/2.zoppoz.workers.dev:443\/https\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/2.zoppoz.workers.dev:443\/https\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/2.zoppoz.workers.dev:443\/https\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/2.zoppoz.workers.dev:443\/https\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100004826","name":"Beijing Natural Science Foundation","doi-asserted-by":"publisher","award":["L223003"],"award-info":[{"award-number":["L223003"]}],"id":[{"id":"10.13039\/501100004826","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62222302"],"award-info":[{"award-number":["62222302"]}],"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":["62273345"],"award-info":[{"award-number":["62273345"]}],"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":["U22B2055"],"award-info":[{"award-number":["U22B2055"]}],"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":["62402494"],"award-info":[{"award-number":["62402494"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100013142","name":"Key Research and Development Project of Hainan Province","doi-asserted-by":"publisher","award":["231111210300"],"award-info":[{"award-number":["231111210300"]}],"id":[{"id":"10.13039\/501100013142","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Pattern Recognition"],"published-print":{"date-parts":[[2026,8]]},"DOI":"10.1016\/j.patcog.2026.113166","type":"journal-article","created":{"date-parts":[[2026,1,28]],"date-time":"2026-01-28T00:23:45Z","timestamp":1769559825000},"page":"113166","update-policy":"https:\/\/2.zoppoz.workers.dev:443\/https\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["MC-MVSNet: When multi-view stereo meets monocular cues"],"prefix":"10.1016","volume":"176","author":[{"ORCID":"https:\/\/2.zoppoz.workers.dev:443\/https\/orcid.org\/0009-0007-4710-8296","authenticated-orcid":false,"given":"Xincheng","family":"Tang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/2.zoppoz.workers.dev:443\/https\/orcid.org\/0000-0003-4852-2345","authenticated-orcid":false,"given":"Mengqi","family":"Rong","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/2.zoppoz.workers.dev:443\/https\/orcid.org\/0000-0002-1155-467X","authenticated-orcid":false,"given":"Bin","family":"Fan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/2.zoppoz.workers.dev:443\/https\/orcid.org\/0000-0001-9834-4087","authenticated-orcid":false,"given":"Hongmin","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/2.zoppoz.workers.dev:443\/https\/orcid.org\/0000-0002-8704-7914","authenticated-orcid":false,"given":"Shuhan","family":"Shen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.patcog.2026.113166_bib0001","series-title":"CVPR","article-title":"Cost volume pyramid based depth inference for multi-view stereo","author":"yang","year":"2020"},{"key":"10.1016\/j.patcog.2026.113166_bib0002","series-title":"CVPR","article-title":"GeoMVSNet: learning multi-view stereo with geometryperception","author":"Zhang","year":"2023"},{"key":"10.1016\/j.patcog.2026.113166_bib0003","series-title":"CVPR","article-title":"Multi-scale geometric consistency guided multi-view stereo","author":"Xu","year":"2019"},{"key":"10.1016\/j.patcog.2026.113166_bib0004","series-title":"AAAI","article-title":"Planar prior assisted patchmatch multi-view stereo","author":"Xu","year":"2020"},{"key":"10.1016\/j.patcog.2026.113166_bib0005","doi-asserted-by":"crossref","first-page":"10579","DOI":"10.1109\/TPAMI.2024.3444912","article-title":"Metric3D v2: a versatile monocular geometric foundation model for zero-shot metric depth and surface normal estimation","volume":"46","author":"Hu","year":"2024","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.patcog.2026.113166_bib0006","series-title":"NIPS","article-title":"Depth anything v2","author":"Yang","year":"2024"},{"key":"10.1016\/j.patcog.2026.113166_bib0007","series-title":"ICCV","article-title":"Vision transformers for dense prediction","author":"Ranftl","year":"2021"},{"key":"10.1016\/j.patcog.2026.113166_bib0008","unstructured":"M. Oquab, T. Darcet, T. Moutakanni, H. Vo, M. Szafraniec, V. Khalidov, P. Fernandez, D. Haziza, F. Massa, A. El-Nouby, et al., DINOv2: learning robust visual features without supervision, Trans. Mach. Learn. Res., 1\u201331, 2024."},{"key":"10.1016\/j.patcog.2026.113166_bib0009","doi-asserted-by":"crossref","first-page":"199","DOI":"10.1007\/s11263-022-01697-3","article-title":"Vis-MVSNet: visibility-aware multi-view stereo network","volume":"16","author":"Zhang","year":"2023","journal-title":"Int. J. Comput. Vis."},{"key":"10.1016\/j.patcog.2026.113166_bib0010","first-page":"1","article-title":"Playing to vision foundation model\u2019s strengths in stereo matching","author":"Liu","year":"2024","journal-title":"IEEE Trans. Intell. Veh."},{"key":"10.1016\/j.patcog.2026.113166_bib0011","series-title":"ECCV","article-title":"MVSNet: depth inference for unstructured multi-view stereo","author":"Yao","year":"2018"},{"key":"10.1016\/j.patcog.2026.113166_bib0012","series-title":"CVPR","article-title":"Recurrent MVSNet for high-resolution multi-view stereo depth inference","author":"Yao","year":"2019"},{"key":"10.1016\/j.patcog.2026.113166_bib0013","series-title":"ECCV","article-title":"Dense hybrid recurrent multi-view stereo net with dynamic consistency checking","author":"Yan","year":"2020"},{"key":"10.1016\/j.patcog.2026.113166_bib0014","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2022.109198","article-title":"Prior depth-based multi-view stereo network for online 3D model reconstruction","volume":"136","author":"Song","year":"2023","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.113166_bib0015","doi-asserted-by":"crossref","first-page":"2040","DOI":"10.1007\/s11263-022-01628-2","article-title":"Learning inverse depth regression for pixelwise visibility-aware multi-view stereo networks","volume":"130","author":"Xu","year":"2022","journal-title":"Int. J. Comput. Vis."},{"key":"10.1016\/j.patcog.2026.113166_bib0016","series-title":"CVPR","article-title":"TransMVSNet: global context-aware multi-view stereo network with transformers","author":"Ding","year":"2022"},{"key":"10.1016\/j.patcog.2026.113166_bib0017","series-title":"ECCV","article-title":"MVSTER: epipolar transformer for efficient multi-view stereo","author":"Wang","year":"2022"},{"key":"10.1016\/j.patcog.2026.113166_bib0018","series-title":"ICCV","article-title":"MonoMVSNet: monocular priors guided multi-view stereo network","author":"Jiang","year":"2025"},{"issue":"11","key":"10.1016\/j.patcog.2026.113166_bib0019","doi-asserted-by":"crossref","first-page":"10060","DOI":"10.1109\/TPAMI.2025.3597148","article-title":"Lightweight and accurate multi-view stereo with confidence-aware diffusion model","volume":"47","author":"Wang","year":"2025","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.patcog.2026.113166_bib0020","doi-asserted-by":"crossref","first-page":"7526","DOI":"10.1109\/TPAMI.2025.3568447","article-title":"Visibility-aware multi-view stereo by surface normal weighting for occlusion robustness","volume":"47","author":"Lee","year":"2025","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.patcog.2026.113166_bib0021","series-title":"CVPR","article-title":"MVSAnywhere: zero-shot multi-view stereo","author":"Izquierdo","year":"2025"},{"key":"10.1016\/j.patcog.2026.113166_bib0022","series-title":"ICCV","article-title":"Metric3D: Towards zero-shot metric 3D prediction from a single image","author":"Yin","year":"2023"},{"key":"10.1016\/j.patcog.2026.113166_bib0023","article-title":"MVSFormer: multi-view stereo by learning robust image features and temperature-based depth","author":"Cao","year":"2023","journal-title":"Trans. Mach. Learn. Res."},{"key":"10.1016\/j.patcog.2026.113166_bib0024","series-title":"CVPR","article-title":"GoMVS: geometrically consistent cost aggregation for multi-view stereo","author":"Wu","year":"2024"},{"key":"10.1016\/j.patcog.2026.113166_bib0025","series-title":"CVPR","article-title":"Massively parallel multiview stereopsis by surface normal diffusion","author":"Galliani","year":"2015"},{"key":"10.1016\/j.patcog.2026.113166_bib0026","doi-asserted-by":"crossref","first-page":"753","DOI":"10.1109\/TIP.2023.3347929","article-title":"EI-MVSNet: epipolar-guided multi-view stereo network with interval-aware label","volume":"33","author":"Chang","year":"2024","journal-title":"IEEE Trans. Image Process."},{"key":"10.1016\/j.patcog.2026.113166_bib0027","series-title":"ICCV","article-title":"When epipolar constraint meets non-local operators in multi-view stereo","author":"Liu","year":"2023"},{"key":"10.1016\/j.patcog.2026.113166_bib0028","first-page":"4945","article-title":"Multi-scale geometric consistency guided and planar prior assisted multi-view stereo","volume":"45","author":"Xu","year":"2022","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.patcog.2026.113166_bib0029","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":"Int. J. Comput. Vis."},{"key":"10.1016\/j.patcog.2026.113166_bib0030","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3072959.3073599","article-title":"Tanks and temples: benchmarking large-scale scene reconstruction","volume":"36","author":"Knapitsch","year":"2017","journal-title":"ACM Trans. Graph."},{"key":"10.1016\/j.patcog.2026.113166_bib0031","series-title":"CVPR","article-title":"A multi-view stereo benchmark with high-resolution images and multi-camera videos","author":"Schops","year":"2017"},{"key":"10.1016\/j.patcog.2026.113166_bib0032","series-title":"CVPR","article-title":"BlendedMVS: a large-scale dataset for generalized multi-view stereo networks","author":"Yao","year":"2020"},{"key":"10.1016\/j.patcog.2026.113166_bib0033","series-title":"ECCV","article-title":"Pixelwise view selection for unstructured multi-view stereo","author":"Sch\u00f6nberger","year":"2016"},{"key":"10.1016\/j.patcog.2026.113166_bib0034","series-title":"CVPR","article-title":"Rethinking depth estimation for multi-view stereo: a unified representation","author":"Peng","year":"2022"},{"key":"10.1016\/j.patcog.2026.113166_bib0035","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2023.109885","article-title":"ARAI-MVSNet: a multi-view stereo depth estimation network with adaptive depth range and depth interval","volume":"144","author":"Zhang","year":"2023","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.113166_bib0036","series-title":"ICCV","article-title":"Constraining depth map geometry for multi-view stereo: a dual-depth approach with saddle-shaped depth cells","author":"Ye","year":"2023"},{"key":"10.1016\/j.patcog.2026.113166_bib0037","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1007\/s11263-024-02337-8","article-title":"Context-aware multi-view stereo network for efficient edge-preserving depth estimation","volume":"133","author":"Su","year":"2025","journal-title":"Int. J. Comput. Vis."},{"key":"10.1016\/j.patcog.2026.113166_bib0038","series-title":"CVPR","article-title":"Multi-view stereo representation revist: region-Aware MVSNet","author":"Zhang","year":"2023"},{"key":"10.1016\/j.patcog.2026.113166_bib0039","series-title":"CVPR","article-title":"IterMVS: iterative probability estimation for efficient multi-view stereo","author":"Wang","year":"2022"},{"key":"10.1016\/j.patcog.2026.113166_bib0040","series-title":"CVPR","article-title":"Generalized binary search network for highly-efficient multi-view stereo","author":"Mi","year":"2022"}],"container-title":["Pattern Recognition"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/2.zoppoz.workers.dev:443\/https\/api.elsevier.com\/content\/article\/PII:S0031320326001317?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/2.zoppoz.workers.dev:443\/https\/api.elsevier.com\/content\/article\/PII:S0031320326001317?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,5,13]],"date-time":"2026-05-13T00:04:32Z","timestamp":1778630672000},"score":1,"resource":{"primary":{"URL":"https:\/\/2.zoppoz.workers.dev:443\/https\/linkinghub.elsevier.com\/retrieve\/pii\/S0031320326001317"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8]]},"references-count":40,"alternative-id":["S0031320326001317"],"URL":"https:\/\/2.zoppoz.workers.dev:443\/https\/doi.org\/10.1016\/j.patcog.2026.113166","relation":{},"ISSN":["0031-3203"],"issn-type":[{"value":"0031-3203","type":"print"}],"subject":[],"published":{"date-parts":[[2026,8]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"MC-MVSNet: When multi-view stereo meets monocular cues","name":"articletitle","label":"Article Title"},{"value":"Pattern Recognition","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/2.zoppoz.workers.dev:443\/https\/doi.org\/10.1016\/j.patcog.2026.113166","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier Ltd. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"113166"}}