{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,9]],"date-time":"2026-05-09T17:34:58Z","timestamp":1778348098460,"version":"3.51.4"},"reference-count":88,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.00494","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"5198-5209","source":"Crossref","is-referenced-by-count":2,"title":["Extending Foundational Monocular Depth Estimators to Fisheye Cameras with Calibration Tokens"],"prefix":"10.1109","author":[{"given":"Suchisrit","family":"Gangopadhyay","sequence":"first","affiliation":[{"name":"Yale University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jung-Hee","family":"Kim","sequence":"additional","affiliation":[{"name":"Michigan State University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xien","family":"Chen","sequence":"additional","affiliation":[{"name":"Yale University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Patrick","family":"Rim","sequence":"additional","affiliation":[{"name":"Yale University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hyoungseob","family":"Park","sequence":"additional","affiliation":[{"name":"Yale University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Alex","family":"Wong","sequence":"additional","affiliation":[{"name":"Yale University"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2019.00291"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00400"},{"key":"ref3","article-title":"Depth pro: Sharp monocular metric depth in less than a second","volume-title":"International Conference on Learning Representations","author":"Bochkovskii","year":"2025"},{"key":"ref4","author":"Burtsev","year":"2020","journal-title":"Memory transformer"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.5244\/C.35.65"},{"key":"ref6","author":"Chen","year":"2024","journal-title":"Uncle: Unsupervised continual learning of depth completion"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01257"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.00567"},{"key":"ref9","author":"Darcet","year":"2023","journal-title":"Vision transformers need registers"},{"key":"ref10","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2019","journal-title":"North American Chapter of the Association for Computational Linguistics"},{"key":"ref11","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","volume-title":"International Conference on Learning Representations","author":"Dosovitskiy","year":"2021"},{"issue":"8","key":"ref12","first-page":"855","article-title":"Close-range camera calibration","volume":"37","author":"Duane","year":"1971","journal-title":"Photogramm. Eng"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.304"},{"key":"ref14","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"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/IROS58592.2024.10802376"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2019.2896963"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01141"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00214"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46484-8_45"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2017.699"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00393"},{"key":"ref22","article-title":"Semantically-guided representation learning for self-supervised monocular depth","volume-title":"International Conference on Learning Representations","author":"Guizilini","year":"2019"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00256"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02514"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR.2004.1333993"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00907"},{"key":"ref27","article-title":"A history of the photographic lens","volume":"145","author":"Kingslake","year":"1989","journal-title":"University of Rochester NY"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00011"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/3DV.2016.32"},{"key":"ref30","article-title":"Sub-token vit embedding via stochastic resonance transformers","volume-title":"International Conference on Machine Learning","author":"Lao","year":"2024"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72913-3_19"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298715"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/s11633-023-1458-0"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2019.2897984"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3179507"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/3DV62453.2024.00056"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2015.2505283"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20086-1_3"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i3.16329"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00594"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1364\/JOSA.54.001060"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.01939"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/iccv48922.2021.01527"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00963"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2025.3628473"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/3DV.2018.00045"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00329"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01196"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3019967"},{"key":"ref50","author":"Rim","year":"2025","journal-title":"Radar-guided polynomial fitting for metric depth estimation"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00591"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01073"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-33715-4_54"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00895"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ACV.1996.572058"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00252"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01003"},{"key":"ref58","first-page":"10347","article-title":"Training data-efficient image transformers and distillation through attention","volume-title":"In Proceedings of the 38th International Conference on Machine Learning","author":"Touvron","year":"2021"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1145\/3618389"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00216"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/ICME51207.2021.9428423"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00225"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00579"},{"issue":"84868497","key":"ref64","article-title":"Targeted adversarial perturbations for monocular depth prediction","volume":"33","author":"Wong","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.2969938"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3058072"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3062602"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73039-9_16"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2023.3290510"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01613"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.25"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02488"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00987"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00347"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00031"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00008"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00578"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01249-6_29"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW63382.2024.00140"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00389"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.00927"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00927"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.52202\/079017-3580"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00043"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01778"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/3DV57658.2022.00077"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1109\/icra55743.2025.11127840"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.700"}],"event":{"name":"2025 IEEE\/CVF International Conference on Computer Vision (ICCV)","location":"Honolulu, HI, USA","start":{"date-parts":[[2025,10,19]]},"end":{"date-parts":[[2025,10,25]]}},"container-title":["2025 IEEE\/CVF International Conference on Computer Vision (ICCV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11443115\/11443287\/11445746.pdf?arnumber=11445746","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T06:20:21Z","timestamp":1777530021000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11445746\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":88,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.00494","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}