{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,2]],"date-time":"2026-06-02T09:25:56Z","timestamp":1780392356114,"version":"3.54.1"},"reference-count":96,"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\/iccv51701.2025.00668","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"7110-7121","source":"Crossref","is-referenced-by-count":1,"title":["Boost 3D Reconstruction Using Diffusion-Based Monocular Camera Calibration"],"prefix":"10.1109","author":[{"given":"Junyuan","family":"Deng","sequence":"first","affiliation":[{"name":"The Hong Kong University of Science and Technology"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wei","family":"Yin","sequence":"additional","affiliation":[{"name":"Horizon Robotics"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaoyang","family":"Guo","sequence":"additional","affiliation":[{"name":"Horizon Robotics"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qian","family":"Zhang","sequence":"additional","affiliation":[{"name":"Horizon Robotics"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaotao","family":"Hu","sequence":"additional","affiliation":[{"name":"The Hong Kong University of Science and Technology"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Weiqiang","family":"Ren","sequence":"additional","affiliation":[{"name":"Horizon Robotics"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiao-Xiao","family":"Long","sequence":"additional","affiliation":[{"name":"Nanjing University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ping","family":"Tan","sequence":"additional","affiliation":[{"name":"The Hong Kong University of Science and Technology"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00773"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/MC.2010.170"},{"key":"ref3","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":"ref4","article-title":"Zoedepth: Zero-shot transfer by combining relative and metric depth","author":"Farooq Bhat","year":"2023","journal-title":"arXiv preprint"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.52202\/075280-3195"},{"key":"ref6","article-title":"Virtual kitti 2","author":"Cabon","year":"2020","journal-title":"arXiv preprint"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01164"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19769-7_32"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"ref10","article-title":"Shapenet: An informationrich 3d model repository","author":"Angel","year":"2015","journal-title":"arXiv preprint"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.350"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.1999.790349"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.261"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72670-5_14"},{"key":"ref16","first-page":"4","article-title":"Mve-a multi-view reconstruction environment","volume":"3","author":"Fuhrmann","year":"2014","journal-title":"GCH"},{"key":"ref17","article-title":"Translation of \u201czur ermittlung eines objektes aus zwei perspektiven mit innerer orientierung\u201d by erwin kruppa (1913)","author":"Gallego","year":"2018","journal-title":"arXiv preprint"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/wacv61041.2025.00083"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6248074"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2001.937611"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-58240-1_13"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/34.574792"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i3.32355"},{"key":"ref24","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume":"33","author":"Ho","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/FG57933.2023.10042701"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3444912"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.00193"},{"key":"ref28","article-title":"Drivingworld: Constructing world model for autonomous driving via video gpt","author":"Hu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/1618452.1618459"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01660"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01839"},{"key":"ref32","volume-title":"Multi-resolution noise for diffusion model training","year":"2023"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00907"},{"key":"ref34","article-title":"Auto-encoding variational bayes","author":"Kingma","year":"2013","journal-title":"arXiv preprint"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2019.102877"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2013.166"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00853"},{"key":"ref38","article-title":"Hyperhuman: Hyper-realistic human generation with latent structural diffusion","author":"Liu","year":"2023","journal-title":"arXiv preprint"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICIIBMS60103.2023.10347625"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00951"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-48375-6_74"},{"key":"ref42","author":"Luo","year":"2023","journal-title":"Latent consistency models: Synthesizing highresolution images with few-step inference"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1023\/A:1007982716991"},{"key":"ref44","article-title":"Derek Hoiem and Rob Fergus","volume-title":"Indoor segmentation and support inference from rgbd images. In The European Conference Computer Vision (ECCV)","author":"Kohli","year":"2012"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02057"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00963"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.1997.609357"},{"key":"ref48","article-title":"Dreamfusion: Text-to-3d using 2d diffusion","author":"Poole","year":"2022","journal-title":"arXiv preprint"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3019967"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01196"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3019967"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01073"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1145\/3528233.3530757"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2643"},{"key":"ref56","article-title":"Progressive distillation for fast sampling of diffusion models","author":"Salimans","year":"2022","journal-title":"arXiv preprint"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2004.1315033"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.445"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2017.272"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00261"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1833"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2006.19"},{"key":"ref63","first-page":"318","article-title":"Acontrario horizon-first vanishing point detection using secondorder grouping laws","volume-title":"Proceedings of the European Conference on Computer Vision (ECCV)","author":"Simon","year":"2018"},{"key":"ref64","article-title":"Denoising diffusion implicit models","author":"Song","year":"2020","journal-title":"arXiv preprint"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6385773"},{"key":"ref66","article-title":"Depth anything at any condition","author":"Sun","year":"2025","journal-title":"arXiv preprint"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00252"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00252"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.1997.609388"},{"key":"ref70","article-title":"DIODE: A dense indoor and outdoor depth dataset","author":"Vasiljevic","year":"2019","journal-title":"CoRR"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73661-2_1"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73661-2_1"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01956"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/IROS45743.2020.9341801"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6248008"},{"key":"ref76","article-title":"Argoverse 2: Next generation datasets for self-driving perception and forecasting","author":"Wilson","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.2969938"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.458"},{"key":"ref79","article-title":"Diffusion models trained with large data are transferable visual models","author":"Xu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00987"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1145\/3687971"},{"key":"ref82","article-title":"Diversedepth: Affine-invariant depth prediction using diverse data","author":"Yin","year":"2020","journal-title":"arXiv preprint"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00027"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3209968"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00830"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00883"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00391"},{"key":"ref88","article-title":"Camera Self-Calibration from Video Sequences: the Kruppa Equations Revisited","volume-title":"PhD thesis","author":"Zeller","year":"1996"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2016.610"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1027"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2007.45"},{"key":"ref92","article-title":"Cameras as rays: Pose estimation via ray diffusion","author":"Jason","year":"2024","journal-title":"arXiv preprint"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1155\/2016\/2802343"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1109\/34.888718"},{"key":"ref96","article-title":"Tame a wild camera: In-the-wild monocular camera calibration","author":"Zhu","year":"2023","journal-title":"NeurIPS"}],"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\/11445677.pdf?arnumber=11445677","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:32:17Z","timestamp":1777613537000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11445677\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":96,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.00668","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}