{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T17:06:38Z","timestamp":1784307998818,"version":"3.55.0"},"reference-count":43,"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:\/\/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:\/\/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:\/\/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:\/\/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:\/\/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:\/\/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:\/\/doi.org\/10.15223\/policy-004"}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Computers & Graphics"],"published-print":{"date-parts":[[2026,8]]},"DOI":"10.1016\/j.cag.2026.104658","type":"journal-article","created":{"date-parts":[[2026,6,10]],"date-time":"2026-06-10T07:25:55Z","timestamp":1781076355000},"page":"104658","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":1,"special_numbering":"C","title":["VAMVSNet: Multi-view stereo based on Variance-Aware Masking and curvature-aware optimization for 3D reconstruction"],"prefix":"10.1016","volume":"138","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-1367-5981","authenticated-orcid":false,"given":"Ning","family":"Zhang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shaowen","family":"Yan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ningfan","family":"Xie","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yinghao","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Gongyan","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shaoyun","family":"Xu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.cag.2026.104658_b1","doi-asserted-by":"crossref","unstructured":"He K, Chen X, Xie S, Li Y, Doll\u00e1r P, Girshick R. Masked autoencoders are scalable vision learners. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition. 2022, p. 16000\u20139.","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"10.1016\/j.cag.2026.104658_b2","doi-asserted-by":"crossref","unstructured":"Cheng S, Xu Z, Zhu S, Li Z, Li LE, 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. 2020, p. 2524\u201334.","DOI":"10.1109\/CVPR42600.2020.00260"},{"key":"10.1016\/j.cag.2026.104658_b3","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."},{"key":"10.1016\/j.cag.2026.104658_b4","first-page":"785","article-title":"MVSNet: Depth Inference for Unstructured Multi-view Stereo","volume":"vol. 11212","author":"Yao","year":"2018"},{"key":"10.1016\/j.cag.2026.104658_b5","series-title":"2019 IEEE\/CVF conference on computer vision and pattern recognition (CVPR)","article-title":"Recurrent MVSNet for High-Resolution Multi-View Stereo Depth Inference","author":"Yao","year":"2019"},{"key":"10.1016\/j.cag.2026.104658_b6","doi-asserted-by":"crossref","unstructured":"Huang P-H, Matzen K, Kopf J, Ahuja N, Huang J-B. Deepmvs: Learning multi-view stereopsis. In: Proceedings of the IEEE conference on computer vision and pattern recognition. 2018, p. 2821\u201330.","DOI":"10.1109\/CVPR.2018.00298"},{"key":"10.1016\/j.cag.2026.104658_b7","series-title":"2019 international conference on 3D vision (3DV)","first-page":"1","article-title":"Mvs2: Deep unsupervised multi-view stereo with multi-view symmetry","author":"Dai","year":"2019"},{"key":"10.1016\/j.cag.2026.104658_b8","doi-asserted-by":"crossref","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. 2024, p. 20207\u201316.","DOI":"10.1109\/CVPR52733.2024.01910"},{"issue":"8","key":"10.1016\/j.cag.2026.104658_b9","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":"2009","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"10.1016\/j.cag.2026.104658_b10","doi-asserted-by":"crossref","unstructured":"Yu Z, Gao S. 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. 2020, p. 1949\u201358.","DOI":"10.1109\/CVPR42600.2020.00202"},{"key":"10.1016\/j.cag.2026.104658_b11","doi-asserted-by":"crossref","unstructured":"Wang F, Galliani S, Vogel C, Pollefeys M. Itermvs: Iterative probability estimation for efficient multi-view stereo. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition. 2022, p. 8606\u201315.","DOI":"10.1109\/CVPR52688.2022.00841"},{"key":"10.1016\/j.cag.2026.104658_b12","doi-asserted-by":"crossref","unstructured":"Wei Z, Zhu Q, Min C, Chen Y, Wang G. Aa-rmvsnet: Adaptive aggregation recurrent multi-view stereo network. In: Proceedings of the IEEE\/CVF international conference on computer vision. 2021, p. 6187\u201396.","DOI":"10.1109\/ICCV48922.2021.00613"},{"key":"10.1016\/j.cag.2026.104658_b13","doi-asserted-by":"crossref","unstructured":"Ding Y, Yuan W, Zhu Q, Zhang H, Liu X, Wang Y, Liu X. Transmvsnet: Global context-aware multi-view stereo network with transformers. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition. 2022, p. 8585\u201394.","DOI":"10.1109\/CVPR52688.2022.00839"},{"key":"10.1016\/j.cag.2026.104658_b14","series-title":"MVSFormer: Multi-view stereo by learning robust image features and temperature-based depth","author":"Cao","year":"2022"},{"key":"10.1016\/j.cag.2026.104658_b15","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.cag.2026.104658_b16","doi-asserted-by":"crossref","DOI":"10.1016\/j.cag.2023.08.014","article-title":"AdaptMVSNet: Efficient multi-view stereo with adaptive convolution and attention fusion","author":"Jiang","year":"2023","journal-title":"Comput Graph"},{"key":"10.1016\/j.cag.2026.104658_b17","doi-asserted-by":"crossref","DOI":"10.1016\/j.cag.2023.08.017","article-title":"An attention-based and deep sparse priori cascade multi-view stereo network for 3D reconstruction","author":"Wang","year":"2023","journal-title":"Comput Graph"},{"key":"10.1016\/j.cag.2026.104658_b18","doi-asserted-by":"crossref","DOI":"10.1016\/j.cag.2024.103954","article-title":"Multi-view depth estimation based on multi-feature aggregation for 3D reconstruction","author":"Zhang","year":"2024","journal-title":"Comput Graph"},{"issue":"1","key":"10.1016\/j.cag.2026.104658_b19","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":"131","author":"Zhang","year":"2023","journal-title":"Int J Comput Vis"},{"key":"10.1016\/j.cag.2026.104658_b20","doi-asserted-by":"crossref","unstructured":"Zhang Z, Peng R, Hu Y, Wang R. Geomvsnet: Learning multi-view stereo with geometry perception. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition. 2023, p. 21508\u201318.","DOI":"10.1109\/CVPR52729.2023.02060"},{"key":"10.1016\/j.cag.2026.104658_b21","doi-asserted-by":"crossref","unstructured":"Vats VK, Joshi S, Crandall DJ, Reza MA, Jung S-h. GC-MVSNet: Multi-view, multi-scale, geometrically-consistent multi-view stereo. In: Proceedings of the IEEE\/CVF winter conference on applications of computer vision. 2024, p. 3242\u201352.","DOI":"10.1109\/WACV57701.2024.00321"},{"key":"10.1016\/j.cag.2026.104658_b22","doi-asserted-by":"crossref","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. 2021, p. 14194\u2013203.","DOI":"10.1109\/CVPR46437.2021.01397"},{"key":"10.1016\/j.cag.2026.104658_b23","article-title":"What uncertainties do we need in bayesian deep learning for computer vision?","volume":"30","author":"Kendall","year":"2017","journal-title":"Adv Neural Inf Process Syst"},{"key":"10.1016\/j.cag.2026.104658_b24","doi-asserted-by":"crossref","unstructured":"Poggi M, Aleotti F, Tosi F, Mattoccia S. On the uncertainty of self-supervised monocular depth estimation. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition. 2020, p. 3227\u201337.","DOI":"10.1109\/CVPR42600.2020.00329"},{"issue":"1\u20134","key":"10.1016\/j.cag.2026.104658_b25","doi-asserted-by":"crossref","first-page":"259","DOI":"10.1016\/0167-2789(92)90242-F","article-title":"Nonlinear total variation based noise removal algorithms","volume":"60","author":"Rudin","year":"1992","journal-title":"Phys D: Nonlinear Phenom"},{"key":"10.1016\/j.cag.2026.104658_b26","doi-asserted-by":"crossref","unstructured":"Barron JT. A general and adaptive robust loss function. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition. 2019, p. 4331\u20139.","DOI":"10.1109\/CVPR.2019.00446"},{"key":"10.1016\/j.cag.2026.104658_b27","doi-asserted-by":"crossref","unstructured":"Qi X, Liao R, Liu Z, Urtasun R, Jia J. Geonet: Geometric neural network for joint depth and surface normal estimation. In: Proceedings of the IEEE conference on computer vision and pattern recognition. 2018, p. 283\u201391.","DOI":"10.1109\/CVPR.2018.00037"},{"key":"10.1016\/j.cag.2026.104658_b28","doi-asserted-by":"crossref","unstructured":"Lin T-Y, Doll\u00e1r P, Girshick R, He K, Hariharan B, Belongie S. Feature pyramid networks for object detection. In: Proceedings of the IEEE conference on computer vision and pattern recognition. 2017, p. 2117\u201325.","DOI":"10.1109\/CVPR.2017.106"},{"key":"10.1016\/j.cag.2026.104658_b29","doi-asserted-by":"crossref","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. 2015, p. 873\u201381.","DOI":"10.1109\/ICCV.2015.106"},{"key":"10.1016\/j.cag.2026.104658_b30","doi-asserted-by":"crossref","unstructured":"Schonberger JL, Frahm J-M. Structure-from-motion revisited. In: Proceedings of the IEEE conference on computer vision and pattern recognition. 2016, p. 4104\u201313.","DOI":"10.1109\/CVPR.2016.445"},{"issue":"7","key":"10.1016\/j.cag.2026.104658_b31","doi-asserted-by":"crossref","first-page":"3062","DOI":"10.1109\/TVCG.2022.3165860","article-title":"Bidirectional hybrid LSTM based recurrent neural network for multi-view stereo","volume":"30","author":"Wei","year":"2022","journal-title":"IEEE Trans Vis Comput Graphics"},{"key":"10.1016\/j.cag.2026.104658_b32","series-title":"2023 IEEE\/CVF international conference on computer vision (ICCV)","first-page":"18042","article-title":"When Epipolar Constraint Meets Non-local Operators in Multi-View Stereo","author":"Liu","year":"2023"},{"key":"10.1016\/j.cag.2026.104658_b33","doi-asserted-by":"crossref","unstructured":"Hu Y, Zhang J, Zhang Z, Weilharter R, Rao Y, Chen K, Yuan R, Fraundorfer F. ICG-MVSNet: Learning Intra-view and Cross-view Relationships for Guidance in Multi-View Stereo. In: IEEE international conference on multimedia and expo. ICME, 2025.","DOI":"10.1109\/ICME59968.2025.11209443"},{"issue":"3","key":"10.1016\/j.cag.2026.104658_b34","doi-asserted-by":"crossref","first-page":"520","DOI":"10.26599\/BDMA.2024.9020075","article-title":"ETV-MVS: Robust visibility-aware multi-view stereo with epipolar line-based transformer","volume":"8","author":"Wang","year":"2025","journal-title":"Big Data Min Anal"},{"issue":"2","key":"10.1016\/j.cag.2026.104658_b35","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"},{"issue":"4","key":"10.1016\/j.cag.2026.104658_b36","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 (ToG)"},{"key":"10.1016\/j.cag.2026.104658_b37","doi-asserted-by":"crossref","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: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition. 2020, p. 1790\u20139.","DOI":"10.1109\/CVPR42600.2020.00186"},{"key":"10.1016\/j.cag.2026.104658_b38","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"12991","article-title":"Generalized binary search network for highly-efficient multi-view stereo","author":"Mi","year":"2022"},{"key":"10.1016\/j.cag.2026.104658_b39","doi-asserted-by":"crossref","unstructured":"Ma X, Gong Y, Wang Q, Huang J, Chen L, Yu F. Epp-mvsnet: Epipolar-assembling based depth prediction for multi-view stereo. In: Proceedings of the IEEE\/CVF international conference on computer vision. 2021, p. 5732\u201340.","DOI":"10.1109\/ICCV48922.2021.00568"},{"key":"10.1016\/j.cag.2026.104658_b40","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. 2022, p. 8645\u201354.","DOI":"10.1109\/CVPR52688.2022.00845"},{"key":"10.1016\/j.cag.2026.104658_b41","doi-asserted-by":"crossref","unstructured":"Ye X, Zhao W, Liu T, Huang Z, Cao Z, Li X. 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. 2023, p. 17661\u201370.","DOI":"10.1109\/ICCV51070.2023.01619"},{"key":"10.1016\/j.cag.2026.104658_b42","doi-asserted-by":"crossref","unstructured":"Zhang Y, Zhu J, Lin L. Multi-view stereo representation revist: Region-aware mvsnet. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition. 2023, p. 17376\u201385.","DOI":"10.1109\/CVPR52729.2023.01667"},{"key":"10.1016\/j.cag.2026.104658_b43","series-title":"European conference on computer vision","first-page":"674","article-title":"Dense hybrid recurrent multi-view stereo net with dynamic consistency checking","author":"Yan","year":"2020"}],"container-title":["Computers & Graphics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0097849326001299?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0097849326001299?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T16:30:27Z","timestamp":1784305827000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0097849326001299"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8]]},"references-count":43,"alternative-id":["S0097849326001299"],"URL":"https:\/\/doi.org\/10.1016\/j.cag.2026.104658","relation":{},"ISSN":["0097-8493"],"issn-type":[{"value":"0097-8493","type":"print"}],"subject":[],"published":{"date-parts":[[2026,8]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"VAMVSNet: Multi-view stereo based on Variance-Aware Masking and curvature-aware optimization for 3D reconstruction","name":"articletitle","label":"Article Title"},{"value":"Computers & Graphics","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.cag.2026.104658","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":"104658"}}