{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,24]],"date-time":"2026-07-24T11:18:54Z","timestamp":1784891934230,"version":"3.55.0"},"reference-count":53,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100013088","name":"Qinglan Project of Jiangsu Province of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100013088","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62473200"],"award-info":[{"award-number":["62473200"]}],"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":["62476238"],"award-info":[{"award-number":["62476238"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Neural Networks"],"published-print":{"date-parts":[[2026,3]]},"DOI":"10.1016\/j.neunet.2025.108219","type":"journal-article","created":{"date-parts":[[2025,10,17]],"date-time":"2025-10-17T00:45:18Z","timestamp":1760661918000},"page":"108219","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":2,"special_numbering":"C","title":["Uncertainty-constrained fusion of single-view and multi-view depth estimation for AR virtual-real occlusion"],"prefix":"10.1016","volume":"195","author":[{"given":"Jia","family":"Liu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shuai","family":"Ding","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yongze","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bin","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lina","family":"Wei","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1930-419X","authenticated-orcid":false,"given":"Dapeng","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"issue":"7","key":"10.1016\/j.neunet.2025.108219_bib0001","doi-asserted-by":"crossref","first-page":"50","DOI":"10.1145\/159544.159581","article-title":"Tracking requirements for augmented reality","volume":"36","author":"Azuma","year":"1993","journal-title":"Communications of the ACM"},{"key":"10.1016\/j.neunet.2025.108219_bib0002","series-title":"Ieee\/cvf conference on computer vision and pattern recognition","first-page":"2842","article-title":"Multi-view depth estimation by fusing single-view depth probability with multi-view geometry","author":"Bae","year":"2022"},{"key":"10.1016\/j.neunet.2025.108219_bib0003","series-title":"Proceedings of the AAAI conference on artificial intelligence","first-page":"10478","article-title":"Monocular 3d object detection with decoupled structured polygon estimation and height-guided depth estimation","volume":"vol. 34","author":"Cai","year":"2020"},{"key":"10.1016\/j.neunet.2025.108219_bib0004","doi-asserted-by":"crossref","first-page":"373","DOI":"10.2478\/jaiscr-2024-0020","article-title":"Exponential state estimation for delayed competitive neural network via stochastic sampled-data control with markov jump parameters under actuator failure","volume":"14","author":"Cao","year":"2024","journal-title":"Journal of Artificial Intelligence and Soft Computing Research"},{"key":"10.1016\/j.neunet.2025.108219_bib0005","series-title":"Ieee\/cvf conference on computer vision and pattern recognition","first-page":"10138","article-title":"Adaptive fusion of single-view and multi-view depth for autonomous driving","author":"Cheng","year":"2024"},{"key":"10.1016\/j.neunet.2025.108219_bib0006","unstructured":"Choi, J., Jung, D., Lee, D., & Kim, C. (2020). Safenet: Self-supervised monocular depth estimation with semantic-aware feature extraction. arXiv preprint arXiv: 2010.02893."},{"key":"10.1016\/j.neunet.2025.108219_bib0007","series-title":"Ieee\/cvf conference on computer vision and pattern recognition","first-page":"5828","article-title":"Scannet: Richly-annotated 3d reconstructions of indoor scenes","author":"Dai","year":"2017"},{"key":"10.1016\/j.neunet.2025.108219_bib0008","series-title":"Ieee\/cvf conference on computer vision and pattern recognition workshops","first-page":"1000","article-title":"Learning depth-guided convolutions for monocular 3d object detection","author":"Ding","year":"2020"},{"key":"10.1016\/j.neunet.2025.108219_bib0009","series-title":"Proceedings of the 33rd annual ACM symposium on user interface software and technology","first-page":"829","article-title":"Depthlab: Real-time 3d interaction with depth maps for mobile augmented reality","author":"Du","year":"2020"},{"key":"10.1016\/j.neunet.2025.108219_bib0010","series-title":"Ieee\/cvf conference on computer vision and pattern recognition","first-page":"15324","article-title":"Deepvideomvs: Multi-view stereo on video with recurrent spatio-temporal fusion","author":"Duzceker","year":"2021"},{"key":"10.1016\/j.neunet.2025.108219_bib0011","article-title":"Depth map prediction from a single image using a multi-scale deep network","volume":"27","author":"Eigen","year":"2014","journal-title":"Advances in Neural Information Processing Systems"},{"issue":"4","key":"10.1016\/j.neunet.2025.108219_bib0012","doi-asserted-by":"crossref","first-page":"1994","DOI":"10.1109\/LRA.2017.2715400","article-title":"Single-view and multi-view depth fusion","volume":"2","author":"F\u00e1cil","year":"2017","journal-title":"IEEE Robotics and Automation Letters"},{"key":"10.1016\/j.neunet.2025.108219_bib0013","doi-asserted-by":"crossref","first-page":"208","DOI":"10.1007\/BF01682023","article-title":"A touring machine: Prototyping 3d mobile augmented reality systems for exploring the urban environment","volume":"1","author":"Feiner","year":"1997","journal-title":"Personal Technologies"},{"key":"10.1016\/j.neunet.2025.108219_bib0014","series-title":"European conference on computer vision","first-page":"228","article-title":"Disentangling object motion and occlusion for unsupervised multi-frame monocular depth","author":"Feng","year":"2022"},{"issue":"6","key":"10.1016\/j.neunet.2025.108219_bib0015","doi-asserted-by":"crossref","first-page":"381","DOI":"10.1145\/358669.358692","article-title":"Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography","volume":"24","author":"Fischler","year":"1981","journal-title":"Communications of the ACM"},{"key":"10.1016\/j.neunet.2025.108219_bib0016","unstructured":"Gal, Y., & Ghahramani, Z. (2015). Bayesian convolutional neural networks with bernoulli approximate variational inference. arXiv preprint arXiv: 1506.02158."},{"key":"10.1016\/j.neunet.2025.108219_bib0017","series-title":"Ieee\/cvf international conference on computer vision","first-page":"3828","article-title":"Digging into self-supervised monocular depth estimation","author":"Godard","year":"2019"},{"key":"10.1016\/j.neunet.2025.108219_bib0018","unstructured":"Guizilini, V., Hou, R., Li, J., Ambrus, R., & Gaidon, A. (2020). Semantically-guided representation learning for self-supervised monocular depth. arXiv preprint arXiv: 2002.12319."},{"key":"10.1016\/j.neunet.2025.108219_bib0019","series-title":"Ieee international symposium on mixed and augmented reality (ismar)","first-page":"62","article-title":"Occlusion matting: realistic occlusion handling for augmented reality applications","author":"Hebborn","year":"2017"},{"key":"10.1016\/j.neunet.2025.108219_bib0020","series-title":"Ieee\/cvf international conference on computer vision","first-page":"2651","article-title":"Multi-view stereo by temporal nonparametric fusion","author":"Hou","year":"2019"},{"key":"10.1016\/j.neunet.2025.108219_bib0021","unstructured":"Im, S., Jeon, H.-G., Lin, S., & Kweon, I. S. (2019). Dpsnet: End-to-end deep plane sweep stereo. arXiv preprint arXiv: 1905.00538."},{"key":"10.1016\/j.neunet.2025.108219_bib0022","series-title":"Ieee and acm international workshop on augmented reality (iwar\u201999)","first-page":"85","article-title":"Marker tracking and hmd calibration for a video-based augmented reality conferencing system","author":"Kato","year":"1999"},{"key":"10.1016\/j.neunet.2025.108219_bib0023","series-title":"European conference on computer vision","first-page":"582","article-title":"Self-supervised monocular depth estimation: Solving the dynamic object problem by semantic guidance","author":"Klingner","year":"2020"},{"key":"10.1016\/j.neunet.2025.108219_bib0024","series-title":"Ieee\/cvf conference on computer vision and pattern recognition","first-page":"21539","article-title":"Learning to fuse monocular and multi-view cues for multi-frame depth estimation in dynamic scenes","author":"Li","year":"2023"},{"key":"10.1016\/j.neunet.2025.108219_bib0025","series-title":"International conference on medical image computing and computer-assisted intervention","first-page":"429","article-title":"Multi-view guidance for self-supervised monocular depth estimation on laparoscopic images via spatio-temporal correspondence","author":"Li","year":"2023"},{"key":"10.1016\/j.neunet.2025.108219_bib0026","series-title":"Proceedings of the AAAI conference on artificial intelligence","first-page":"1486","article-title":"Bevstereo: Enhancing depth estimation in multi-view 3d object detection with temporal stereo","volume":"vol. 37","author":"Li","year":"2023"},{"key":"10.1016\/j.neunet.2025.108219_bib0027","series-title":"Proceedings of the AAAI conference on artificial intelligence","first-page":"1477","article-title":"Bevdepth: Acquisition of reliable depth for multi-view 3d object detection","volume":"vol. 37","author":"Li","year":"2023"},{"key":"10.1016\/j.neunet.2025.108219_bib0028","doi-asserted-by":"crossref","DOI":"10.1016\/j.neunet.2025.107565","article-title":"Semantic discrete decoder based on adaptive pixel clustering for monocular depth estimation","volume":"189","author":"Liu","year":"2025","journal-title":"Neural Networks"},{"key":"10.1016\/j.neunet.2025.108219_bib0029","unstructured":"Loshchilov, I., & Hutter, F. (2017). Decoupled weight decay regularization. arXiv preprint arXiv: 1711.05101."},{"issue":"4","key":"10.1016\/j.neunet.2025.108219_bib0030","doi-asserted-by":"crossref","first-page":"71","DOI":"10.1145\/3386569.3392377","article-title":"Consistent video depth estimation","volume":"39","author":"Luo","year":"2020","journal-title":"ACM Transactions on Graphics"},{"key":"10.1016\/j.neunet.2025.108219_bib0031","series-title":"Proceedings of the 18th ACM international conference on multimedia","first-page":"1485","article-title":"Torchvision the machine-vision package of torch","author":"Marcel","year":"2010"},{"key":"10.1016\/j.neunet.2025.108219_bib0032","series-title":"Ieee\/cvf conference on computer vision and pattern recognition","first-page":"9685","article-title":"Boosting monocular depth estimation models to high-resolution via content-adaptive multi-resolution merging","author":"Miangoleh","year":"2021"},{"key":"10.1016\/j.neunet.2025.108219_bib0033","series-title":"International conference on dependability and complex systems","first-page":"358","article-title":"Capabilities of arcore and arkit platforms for ar\/vr applications","author":"Nowacki","year":"2020"},{"key":"10.1016\/j.neunet.2025.108219_bib0034","first-page":"8024","article-title":"Pytorch: An imperative style, high-performance deep learning library","volume":"32","author":"Paszke","year":"2019","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.neunet.2025.108219_bib0035","unstructured":"Saunders, K., Manso, L. J., & Vogiatzis, G. (2024). Baseboostdepth: Exploiting larger baselines for self-supervised monocular depth estimation. arXiv preprint arXiv: 2407.20437."},{"key":"10.1016\/j.neunet.2025.108219_bib0036","series-title":"European conference on computer vision","first-page":"1","article-title":"Simplerecon: 3d reconstruction without 3d convolutions","author":"Sayed","year":"2022"},{"key":"10.1016\/j.neunet.2025.108219_bib0037","series-title":"European conference on computer vision","first-page":"104","article-title":"Deltas: Depth estimation by learning triangulation and densification of sparse points","author":"Sinha","year":"2020"},{"key":"10.1016\/j.neunet.2025.108219_bib0038","first-page":"1","article-title":"Robust dissipative sliding mode control synchronization of memristive inertial competitive neural networks with time-varying delay","author":"Subhashri","year":"2025","journal-title":"The European Physical Journal Special Topics"},{"issue":"1","key":"10.1016\/j.neunet.2025.108219_bib0039","doi-asserted-by":"crossref","first-page":"497","DOI":"10.1109\/TPAMI.2023.3322549","article-title":"Sc-depthv3: Robust self-supervised monocular depth estimation for dynamic scenes","volume":"46","author":"Sun","year":"2023","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"10.1016\/j.neunet.2025.108219_bib0040","series-title":"Proceedings of the december 9-11, 1968, fall joint computer conference, part i.","first-page":"757","article-title":"A head-mounted three dimensional display","author":"Sutherland","year":"1968"},{"key":"10.1016\/j.neunet.2025.108219_bib0041","series-title":"Second international symposium on wearable computers","first-page":"168","article-title":"A wearable computer system with augmented reality to support terrestrial navigation","author":"Thomas","year":"1998"},{"issue":"4","key":"10.1016\/j.neunet.2025.108219_bib0042","doi-asserted-by":"crossref","first-page":"531","DOI":"10.1109\/TVCG.2014.27","article-title":"Global localization from monocular slam on a mobile phone","volume":"20","author":"Ventura","year":"2014","journal-title":"IEEE Transactions on Visualization and Computer Graphics"},{"key":"10.1016\/j.neunet.2025.108219_bib0043","series-title":"International conference on 3d vision (3DV)","first-page":"248","article-title":"Mvdepthnet: Real-time multiview depth estimation neural network","author":"Wang","year":"2018"},{"key":"10.1016\/j.neunet.2025.108219_bib0044","doi-asserted-by":"crossref","DOI":"10.1016\/j.inffus.2024.102363","article-title":"Self-supervised multi-frame depth estimation with visual-inertial pose transformer and monocular guidance","volume":"108","author":"Wang","year":"2024","journal-title":"Information Fusion"},{"key":"10.1016\/j.neunet.2025.108219_bib0045","series-title":"International conference on 3d vision (3DV)","first-page":"514","article-title":"Dynocc: Learning single-view depth from dynamic occlusion cues","author":"Wang","year":"2020"},{"key":"10.1016\/j.neunet.2025.108219_bib0046","series-title":"Ieee\/cvf conference on computer vision and pattern recognition","first-page":"19809","article-title":"Occlusion-aware cost constructor for light field depth estimation","author":"Wang","year":"2022"},{"key":"10.1016\/j.neunet.2025.108219_bib0047","series-title":"Ieee\/cvf conference on computer vision and pattern recognition","first-page":"9053","article-title":"Virtual occlusions through implicit depth","author":"Watson","year":"2023"},{"key":"10.1016\/j.neunet.2025.108219_bib0048","series-title":"International conference on 3d vision (3DV)","first-page":"464","article-title":"Channel-wise attention-based network for self-supervised monocular depth estimation","author":"Yan","year":"2021"},{"key":"10.1016\/j.neunet.2025.108219_bib0049","first-page":"21875","article-title":"Depth anything v2","volume":"37","author":"Yang","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.neunet.2025.108219_bib0050","series-title":"Ieee\/cvf conference on computer vision and pattern recognition","first-page":"8574","article-title":"Mvs2d: Efficient multi-view stereo via attention-driven 2d convolutions","author":"Yang","year":"2022"},{"key":"10.1016\/j.neunet.2025.108219_bib0051","doi-asserted-by":"crossref","DOI":"10.1016\/j.engappai.2022.104862","article-title":"Self-supervised monocular depth estimation in dynamic scenes with moving instance loss","volume":"112","author":"Yue","year":"2022","journal-title":"Engineering Applications of Artificial Intelligence"},{"key":"10.1016\/j.neunet.2025.108219_bib0052","article-title":"B2CNet: A progressive change boundary-to-center refinement network for multi-temporal remote sensing images change detection","author":"Zhang","year":"2024","journal-title":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing"},{"key":"10.1016\/j.neunet.2025.108219_bib0053","series-title":"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"}],"container-title":["Neural Networks"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0893608025011001?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0893608025011001?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,3,11]],"date-time":"2026-03-11T19:20:29Z","timestamp":1773256829000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0893608025011001"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3]]},"references-count":53,"alternative-id":["S0893608025011001"],"URL":"https:\/\/doi.org\/10.1016\/j.neunet.2025.108219","relation":{},"ISSN":["0893-6080"],"issn-type":[{"value":"0893-6080","type":"print"}],"subject":[],"published":{"date-parts":[[2026,3]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Uncertainty-constrained fusion of single-view and multi-view depth estimation for AR virtual-real occlusion","name":"articletitle","label":"Article Title"},{"value":"Neural Networks","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.neunet.2025.108219","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":"108219"}}