{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T22:40:06Z","timestamp":1782945606031,"version":"3.54.5"},"reference-count":215,"publisher":"Tsinghua University Press","issue":"2","funder":[{"DOI":"10.13039\/501100004731","name":"Zhejiang Provincial Natural Science Foundation of China","doi-asserted-by":"publisher","award":["LD25F030001"],"award-info":[{"award-number":["LD25F030001"]}],"id":[{"id":"10.13039\/501100004731","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100020707","name":"Information Technology Center","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100020707","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100011442","name":"State Key Lab of CAD&CG","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100011442","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004835","name":"Zhejiang University","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100004835","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Comp. Visual. Med."],"published-print":{"date-parts":[[2026,4]]},"DOI":"10.26599\/cvm.2025.9450517","type":"journal-article","created":{"date-parts":[[2026,1,27]],"date-time":"2026-01-27T20:28:49Z","timestamp":1769545729000},"page":"243-271","source":"Crossref","is-referenced-by-count":1,"title":["Towards Depth Foundation Models: Recent Trends in Vision-Based Depth Estimation"],"prefix":"10.26599","volume":"12","author":[{"given":"Zhen","family":"Xu","sequence":"first","affiliation":[{"name":"Zhejiang University,Hangzhou,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hongyu","family":"Zhou","sequence":"additional","affiliation":[{"name":"Zhejiang University,Hangzhou,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sida","family":"Peng","sequence":"additional","affiliation":[{"name":"Zhejiang University,Hangzhou,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Haotong","family":"Lin","sequence":"additional","affiliation":[{"name":"Zhejiang University,Hangzhou,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Haoyu","family":"Guo","sequence":"additional","affiliation":[{"name":"Shanghai AI Lab,Shanghai,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiahao","family":"Shao","sequence":"additional","affiliation":[{"name":"Zhejiang University,Hangzhou,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Peishan","family":"Yang","sequence":"additional","affiliation":[{"name":"Zhejiang University,Hangzhou,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qinglin","family":"Yang","sequence":"additional","affiliation":[{"name":"Zhejiang University,Hangzhou,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sheng","family":"Miao","sequence":"additional","affiliation":[{"name":"Zhejiang University,Hangzhou,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xingyi","family":"He","sequence":"additional","affiliation":[{"name":"Zhejiang University,Hangzhou,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yifan","family":"Wang","sequence":"additional","affiliation":[{"name":"Zhejiang University,Hangzhou,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yue","family":"Wang","sequence":"additional","affiliation":[{"name":"Zhejiang University,Hangzhou,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ruizhen","family":"Hu","sequence":"additional","affiliation":[{"name":"Shenzhen University,Shenzhen,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yiyi","family":"Liao","sequence":"additional","affiliation":[{"name":"Zhejiang University,Hangzhou,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaowei","family":"Zhou","sequence":"additional","affiliation":[{"name":"Zhejiang University,Hangzhou,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hujun","family":"Bao","sequence":"additional","affiliation":[{"name":"Zhejiang University,Hangzhou,China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"11138","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-24797-2_4"},{"key":"ref2","article-title":"Word embeddings: A survey","author":"Almeida","year":"2019","journal-title":"arXiv preprint"},{"key":"ref3","article-title":"Attention is all you need","author":"Vaswani","year":"2017","journal-title":"arXiv preprint"},{"key":"ref4","first-page":"4171","article-title":"BERT: Pretraining of deep bidirectional transformers for language understanding","volume-title":"Proceedings of the Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies","volume":"1","author":"Devlin","year":"2019"},{"key":"ref5","article-title":"Language models are few-shot learners","author":"Brown","year":"2020","journal-title":"arXiv preprint"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"ref7","article-title":"DINOv2: Learning robust visual features without supervision","author":"Oquab","year":"2023","journal-title":"arXiv preprint"},{"key":"ref8","article-title":"DINOv3","author":"Sim\u00e9oni","year":"2025","journal-title":"arXiv preprint"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref11","article-title":"SAM 2: Segment anything in images and videos","author":"Ravi","year":"2024","journal-title":"arXiv preprint"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref13","article-title":"Denoising diffusion probabilistic models","author":"Ho","year":"2020","journal-title":"arXiv preprint"},{"key":"ref14","article-title":"A2D2: Audi autonomous driving dataset","author":"Geyer","year":"2020","journal-title":"arXiv preprint"},{"key":"ref15","article-title":"Argoverse 2: Next generation datasets for self-driving perception and forecasting","volume-title":"arXiv preprint","author":"Wilson","year":"2023"},{"key":"ref16","article-title":"Trust, but verify: Cross-modality fusion for HD map change detection","author":"Lambert","year":"2021","journal-title":"arXiv preprint"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.350"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00256"},{"key":"ref19","article-title":"DIML\/CVL RGB-D dataset: 2M RGB-D images of natural indoor and outdoor scenes","author":"Cho","year":"2021","journal-title":"arXiv preprint"},{"key":"ref20","article-title":"DIODE: A dense indoor and outdoor DEpth dataset","author":"Vasiljevic","year":"2019","journal-title":"arXiv preprint"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3068942"},{"key":"ref22","article-title":"Habitat-matterport 3D dataset (HM3D): 1000 large-scale 3D environments for embodied AI","author":"Ramakrishnan","year":"2021","journal-title":"arXiv preprint"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-11015-4_25"},{"key":"ref24","article-title":"One thousand and one hours: Self-driving motion prediction dataset","author":"Houston","year":"2020","journal-title":"arXiv preprint"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58536-5_35"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01164"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-33715-4_54"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC48978.2021.9565009"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00391"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6248074"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00099"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-019-2803-x"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00895"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.272"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00252"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1038\/s41597-019-0168-5"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0902-9"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00186"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02112"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00883"},{"key":"ref41","article-title":"ARKitScenes: A diverse real-world dataset for 3D indoor scene understanding using mobile RGB-D data","author":"Baruch","year":"2021","journal-title":"arXiv preprint"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/3DV.2017.00081"},{"key":"ref43","article-title":"The replica dataset: A digital replica of indoor spaces","author":"Straub","year":"2019","journal-title":"arXiv preprint"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01271"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.261"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/iccv51070.2023.00008"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-33783-3_44"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.438"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01578"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2018.00275"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00495"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr46437.2021.00883"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00482"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/IROS45743.2020.9341801"},{"key":"ref55","article-title":"Virtual KITTI 2","author":"Cabon","year":"2020","journal-title":"arXiv preprint"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00297"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00298"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1145\/3355089.3356528"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00084"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/ICME51207.2021.9428423"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/iccv51070.2023.01818"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00843"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298925"},{"key":"ref64","first-page":"2366","article-title":"Depth map prediction from a single image using a multi-scale deep network","volume-title":"Proceedings of the 28th International Conference on Neural Information Processing Systems","volume":"2","author":"Eigen","year":"2014"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.699"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00214"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00077"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3019967"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00027"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01196"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00907"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00987"},{"key":"ref73","article-title":"Depth anything v2","author":"Yang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00496"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00963"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2025.3628473"},{"key":"ref77","article-title":"MoGe-2: Accurate monocular geometry with metric scale and sharp details","author":"Wang","year":"2025","journal-title":"arXiv preprint"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.17"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00614"},{"key":"ref80","first-page":"22158","article-title":"Hierarchical neural architecture search for deep stereo matching","volume-title":"Proceedings of the 34th International Conference on Neural Information Processing Systems","author":"Cheng","year":"2020"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/3DV53792.2021.00032"},{"key":"ref82","article-title":"Mono2Stereo: Monocular knowledge transfer for enhanced stereo matching","author":"Wang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.59"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.106"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01237-3_47"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01956"},{"key":"ref87","article-title":"MVSFormer++: Revealing the devil in Transformer\u2019s details for multi-view stereo","author":"Cao","year":"2024","journal-title":"arXiv preprint"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73220-1_5"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00499"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1145\/3386569.3392377"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00804"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00868"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.02127"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.00193"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.01645"},{"key":"ref96","first-page":"1161","article-title":"Learning depth from single monocular images","volume-title":"Proceedings of the 19th International Conference on Neural Information Processing Systems","author":"Saxena","year":"2005"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-006-0031-y"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-88690-7_3"},{"key":"ref99","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2008.132"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.304"},{"key":"ref101","doi-asserted-by":"publisher","DOI":"10.1109\/3DV.2016.32"},{"key":"ref102","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01987"},{"key":"ref103","article-title":"The surprising effectiveness of diffusion models for optical flow and monocular depth estimation","author":"Saxena","year":"2023","journal-title":"arXiv preprint"},{"key":"ref104","article-title":"DiverseDepth: Affine-invariant depth prediction using diverse data","author":"Yin","year":"2020","journal-title":"arXiv preprint"},{"key":"ref105","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00996"},{"key":"ref106","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00400"},{"key":"ref107","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19769-7_28"},{"key":"ref108","article-title":"Improving deep regression with ordinal entropy","author":"Zhang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref109","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-024-02293-3"},{"key":"ref110","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00830"},{"key":"ref111","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3444912"},{"key":"ref112","article-title":"Depth pro: Sharp monocular metric depth in less than a second","author":"Bochkovskii","year":"2024","journal-title":"arXiv preprint"},{"key":"ref113","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00218"},{"key":"ref114","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00393"},{"key":"ref115","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00037"},{"key":"ref116","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72670-5_14"},{"key":"ref117","doi-asserted-by":"publisher","DOI":"10.1109\/iccv48922.2021.01061"},{"key":"ref118","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2010.11929"},{"key":"ref119","article-title":"DepthMaster: Taming diffusion models for monocular depth estimation","author":"Song","year":"2025","journal-title":"arXiv preprint"},{"key":"ref120","article-title":"What matters when repurposing diffusion models for general dense perception tasks?","volume-title":"arXiv preprint","author":"Xu","year":"2024"},{"key":"ref121","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-91569-7_14"},{"key":"ref122","article-title":"Scaling 4D representations","author":"Carreira","year":"2024","journal-title":"arXiv preprint"},{"key":"ref123","article-title":"ZoeDepth: Zero-shot transfer by combining relative and metric depth","author":"Bhat","year":"2023","journal-title":"arXiv preprint"},{"key":"ref124","article-title":"Marigold-DC: Zero-shot monocular depth completion with guided diffusion","author":"Viola","year":"2024","journal-title":"arXiv preprint"},{"key":"ref125","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01591"},{"key":"ref126","article-title":"Depth any video with scalable synthetic data","author":"Yang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref127","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.117"},{"key":"ref128","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00567"},{"key":"ref129","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00339"},{"key":"ref130","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00027"},{"key":"ref131","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19824-3_17"},{"key":"ref132","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00167"},{"key":"ref133","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00203"},{"key":"ref134","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01290"},{"key":"ref135","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref136","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.243"},{"key":"ref137","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19824-3_16"},{"key":"ref138","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00350"},{"key":"ref139","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3298645"},{"key":"ref140","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00198"},{"key":"ref141","article-title":"CroCo: Self-supervised pretraining for 3D vision tasks by cross-view completion","author":"Weinzaepfel","year":"2022","journal-title":"arXiv preprint"},{"key":"ref142","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01630"},{"key":"ref143","doi-asserted-by":"publisher","DOI":"10.1201\/9781420049176"},{"key":"ref144","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02099"},{"key":"ref145","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2025.3569218"},{"key":"ref146","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.00103"},{"key":"ref147","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00588"},{"key":"ref148","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02036"},{"key":"ref149","article-title":"ZeroStereo: Zero-shot stereo matching from single images","author":"Wang","year":"2025","journal-title":"arXiv preprint"},{"key":"ref150","article-title":"Stereo anything: Unifying zero-shot stereo matching with large-scale mixed data","author":"Guo","year":"2024","journal-title":"arXiv preprint"},{"key":"ref151","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_42"},{"key":"ref152","doi-asserted-by":"publisher","DOI":"10.5244\/C.25.14"},{"key":"ref153","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46487-9_31"},{"key":"ref154","first-page":"4104","article-title":"Structure-frommotion revisited","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","author":"Sch\u00f6nberger","year":"2016"},{"key":"ref155","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-44480-7_21"},{"key":"ref156","doi-asserted-by":"publisher","DOI":"10.1017\/cbo9780511811685"},{"key":"ref157","first-page":"593","article-title":"FastSLAM: A factored solution to the simultaneous localization and mapping problem","volume-title":"Proceedings of the AAAI Conference on Artificial Intelligence","author":"Montemerlo","year":"2002"},{"key":"ref158","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2007.1049"},{"key":"ref159","doi-asserted-by":"publisher","DOI":"10.1109\/70.34770"},{"key":"ref160","doi-asserted-by":"publisher","DOI":"10.1177\/02783649922066213"},{"key":"ref161","doi-asserted-by":"publisher","DOI":"10.1145\/1531326.1531330"},{"key":"ref162","doi-asserted-by":"publisher","DOI":"10.1109\/3DV.2018.00037"},{"key":"ref163","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00838"},{"key":"ref164","article-title":"Learning a multi-view stereo machine","author":"Kar","year":"2017","journal-title":"arXiv preprint"},{"key":"ref165","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.253"},{"key":"ref166","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00260"},{"key":"ref167","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00257"},{"key":"ref168","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00493"},{"key":"ref169","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58545-7_44"},{"key":"ref170","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00841"},{"key":"ref171","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19821-2_33"},{"key":"ref172","article-title":"MVSFormer: Multi-view stereo by learning robust image features and temperature-based depth","author":"Cao","year":"2022","journal-title":"arXiv preprint"},{"key":"ref173","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72633-0_1"},{"key":"ref174","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02049"},{"key":"ref175","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02125"},{"key":"ref176","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00983"},{"key":"ref177","doi-asserted-by":"publisher","DOI":"10.1109\/3dv66043.2025.00013"},{"key":"ref178","article-title":"MASt3R-SfM: A fully-integrated solution for unconstrained structure-frommotion","author":"Duisterhof","year":"2024","journal-title":"arXiv preprint"},{"key":"ref179","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00608"},{"key":"ref180","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00497"},{"key":"ref181","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02043"},{"key":"ref182","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02042"},{"key":"ref183","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00108"},{"key":"ref184","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00981"},{"key":"ref185","doi-asserted-by":"publisher","DOI":"10.1109\/3DV66043.2025.00086"},{"key":"ref186","article-title":"MonST3R: A simple approach for estimating geometry in the presence of motion","author":"Zhang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref187","article-title":"PF-LRM: Pose-free large reconstruction model for joint pose and shape prediction","author":"Wang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref188","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00181"},{"key":"ref189","doi-asserted-by":"publisher","DOI":"10.1109\/3DV50981.2020.00061"},{"key":"ref190","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02126"},{"key":"ref191","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19827-4_1"},{"key":"ref192","doi-asserted-by":"publisher","DOI":"10.1145\/237170.237269"},{"key":"ref193","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19824-3_9"},{"key":"ref194","article-title":"MonoSDF: Exploring monocular geometric cues for neural implicit surface reconstruction","author":"Yu","year":"2022","journal-title":"arXiv preprint"},{"key":"ref195","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_24"},{"key":"ref196","doi-asserted-by":"publisher","DOI":"10.1145\/3592433"},{"key":"ref197","article-title":"StreetSurf: Extending multi-view implicit surface reconstruction to street views","author":"Guo","year":"2023","journal-title":"arXiv preprint"},{"key":"ref198","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73404-5_6"},{"key":"ref199","article-title":"InstantSplat: Sparse-view Gaussian splatting in seconds","volume-title":"arXiv preprint","author":"Fan","year":"2024"},{"key":"ref200","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2025.3647952"},{"key":"ref201","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01054"},{"key":"ref202","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73464-9_10"},{"key":"ref203","doi-asserted-by":"publisher","DOI":"10.1109\/cvprw67362.2025.00156"},{"key":"ref204","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2025.XXI.040"},{"key":"ref205","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01708"},{"key":"ref206","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10611269"},{"key":"ref207","volume-title":"Video generation models as world simulators","year":"2024"},{"key":"ref208","article-title":"CogVideo: Large-scale pretraining for text-to-video generation via transformers","author":"Hong","year":"2022","journal-title":"arXiv preprint"},{"key":"ref209","article-title":"CogVideoX: Text-to-video diffusion models with an expert transformer","author":"Yang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref210","article-title":"AVID: Adapting video diffusion models to world models","author":"Rigter","year":"2024","journal-title":"arXiv preprint"},{"key":"ref211","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.02020"},{"key":"ref212","article-title":"How far is video generation from world model: A physical law perspective","author":"Kang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref213","doi-asserted-by":"publisher","DOI":"10.1145\/3687919"},{"key":"ref214","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01893"},{"key":"ref215","doi-asserted-by":"publisher","DOI":"10.1145\/3610543.3626173"}],"container-title":["Computational Visual Media"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10750449\/11435620\/11366109.pdf?arnumber=11366109","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,17]],"date-time":"2026-03-17T20:23:17Z","timestamp":1773778997000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11366109\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4]]},"references-count":215,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.26599\/cvm.2025.9450517","relation":{},"ISSN":["2096-0662","2096-0433"],"issn-type":[{"value":"2096-0662","type":"electronic"},{"value":"2096-0433","type":"print"}],"subject":[],"published":{"date-parts":[[2026,4]]}}}