{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,26]],"date-time":"2026-10-26T18:50:15Z","timestamp":1793040615933,"version":"4.5.0"},"reference-count":61,"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"}],"funder":[{"DOI":"10.13039\/100022832","name":"Hong Kong Centre for Logistics Robotics","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100022832","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.02570","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"27681-27691","source":"Crossref","is-referenced-by-count":9,"title":["BridgeDepth: Bridging Monocular and Stereo Reasoning with Latent Alignment"],"prefix":"10.1109","author":[{"given":"Tongfan","family":"Guan","sequence":"first","affiliation":[{"name":"The Chinese University of Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiaxin","family":"Guo","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chen","family":"Wang","sequence":"additional","affiliation":[{"name":"University at Buffalo,Spatial AI & Robotics Lab"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yun-Hui","family":"Liu","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52688.2022.00286"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.00103"},{"key":"ref3","author":"Bochkovskii","year":"2024","journal-title":"Depth pro: Sharp monocular metric depth in less than a second. arXiv preprint arXiv:2410.02073"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00567"},{"key":"ref5","article-title":"Motif channel opened in a whitebox: Stereo matching via motif correlation graph","author":"Chen","year":"2024","journal-title":"arXiv preprint"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00588"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2947374"},{"key":"ref8","article-title":"Hierarchical neural architecture search for deep stereo matching","author":"Cheng","year":"2020","journal-title":"Advances in Neural Information Processing Systems, 33"},{"key":"ref9","article-title":"An image is worth 16 \u00d7 16 words: Transformers for image recognition at scale","author":"Dosovitskiy","journal-title":"arXiv preprint"},{"key":"ref10","first-page":"2366","article-title":"Depth map prediction from a single image using a multi-scale deep network","author":"Eigen","year":"2014","journal-title":"Advances in neural information processing systems"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72670-5_14"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6248074"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00522"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19824-3_16"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00339"},{"key":"ref16","article-title":"Lotus: Diffusion-based visual foundation model for high-quality dense prediction","author":"He","year":"2024","journal-title":"arXiv preprint"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref18","article-title":"Gaussian error linear units (gelus)","author":"Hendrycks","year":"2016","journal-title":"arXiv preprint"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2007.1166"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01658"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02036"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00307"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00907"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.17"},{"key":"ref25","article-title":"From big to small: Multi-scale local planar guidance for monocular depth estimation","author":"Han Lee","journal-title":"arXiv preprint"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01578"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01867"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00614"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/3DV53792.2021.00032"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01167"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.438"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298925"},{"key":"ref34","article-title":"Dinov2: Learning robust visual features without supervision","author":"Oquab","year":"2023","journal-title":"arXiv preprint arXiv:2304.07193"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00963"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2025.3628473"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3019967"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01196"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00526"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-11752-2_3"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2017.272"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01369"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19824-3_17"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58536-5_24"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00496"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01863"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01647"},{"key":"ref49","article-title":"Foundationstereo: Zeroshot stereo matching","author":"Wen","year":"2025","journal-title":"arXiv preprint"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01264"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02099"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2025.3569218"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00987"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.52202\/079017-0688"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00830"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.02049"},{"issue":"65","key":"ref57","first-page":"1","article-title":"Stereo matching by training a convolutional neural network to compare image patches","volume":"17","author":"LeCun","year":"2016","journal-title":"Journal of Machine Learning Research"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2019.00027"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58536-5_25"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72946-1_9"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00134"}],"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\/11445223.pdf?arnumber=11445223","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:01:00Z","timestamp":1777611660000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11445223\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":61,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.02570","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}