{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,23]],"date-time":"2026-04-23T14:56:18Z","timestamp":1776956178672,"version":"3.51.4"},"reference-count":78,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"7","license":[{"start":{"date-parts":[[2025,7,1]],"date-time":"2025-07-01T00:00:00Z","timestamp":1751328000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,7,1]],"date-time":"2025-07-01T00:00:00Z","timestamp":1751328000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,7,1]],"date-time":"2025-07-01T00:00:00Z","timestamp":1751328000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["92270116"],"award-info":[{"award-number":["92270116"]}],"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":["632B2031"],"award-info":[{"award-number":["632B2031"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Intell. Transport. Syst."],"published-print":{"date-parts":[[2025,7]]},"DOI":"10.1109\/tits.2025.3571027","type":"journal-article","created":{"date-parts":[[2025,6,2]],"date-time":"2025-06-02T18:03:28Z","timestamp":1748887408000},"page":"9609-9624","source":"Crossref","is-referenced-by-count":1,"title":["Self-Supervised Multi-Camera Collaborative Depth Prediction With Latent Diffusion Models"],"prefix":"10.1109","volume":"26","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5298-6057","authenticated-orcid":false,"given":"Jialei","family":"Xu","sequence":"first","affiliation":[{"name":"School of Computer Science and Technology, Harbin Institute of Technology, Harbin, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8857-1785","authenticated-orcid":false,"given":"Xianming","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Harbin Institute of Technology, Harbin, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3449-6537","authenticated-orcid":false,"given":"Yuanchao","family":"Bai","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Harbin Institute of Technology, Harbin, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5694-505X","authenticated-orcid":false,"given":"Junjun","family":"Jiang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Harbin Institute of Technology, Harbin, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7333-9975","authenticated-orcid":false,"given":"Xiangyang","family":"Ji","sequence":"additional","affiliation":[{"name":"Department of Automation, Tsinghua University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/MRA.2010.936946"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/MRA.2007.339608"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1162\/pres.1997.6.4.355"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/AERO.2016.7500674"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2022.3159275"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2023.3250744"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2022.3219604"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2022.3179365"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2023.3294642"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2022.3193421"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3249223"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00257"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6248074"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3150884"},{"key":"ref15","article-title":"SurroundDepth: Entangling surrounding views for selfsupervised multi-camera depth estimation","author":"Wei","year":"2022","journal-title":"arXiv:2204.03636"},{"key":"ref16","article-title":"BEVScope: Enhancing self-supervised depth estimation leveraging bird\u2019s-eye-view in dynamic scenarios","author":"Mao","year":"2023","journal-title":"arXiv:2306.11598"},{"key":"ref17","first-page":"4032","article-title":"Selfsupervised surround-view depth estimation with volumetric feature fusion","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Kim"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58568-6_12"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00256"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01164"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.350"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00252"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548394"},{"key":"ref24","first-page":"2366","article-title":"Depth map prediction from a single image using a multi-scale deep network","volume-title":"Proc. Adv. Neural Inf. Process. Syst., Annu. Conf. Neural Inf. Process. Syst.","volume":"27","author":"Eigen"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2832296"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2015.2505283"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00027"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2019.2929202"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-33715-4_54"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1177\/0278364913491297"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00214"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00400"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1017\/S096249291700006X"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.700"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00393"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1023\/A:1014573219977"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2012.156"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.699"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01413"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00493"},{"key":"ref41","article-title":"Learning unsupervised multi-view stereopsis via robust photometric consistency","author":"Khot","year":"2019","journal-title":"arXiv:1905.02706"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611807"},{"key":"ref43","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Ho"},{"key":"ref44","first-page":"2256","article-title":"Deep unsupervised learning using nonequilibrium thermodynamics","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Sohl-Dickstein"},{"key":"ref45","first-page":"3836","article-title":"Adding conditional control to text-toimage diffusion models","volume-title":"Proc. IEEE\/CVF Int. Conf. Comput. Vis.","author":"Zhang"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00907"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72670-5_14"},{"key":"ref49","first-page":"39443","article-title":"The surprising effectiveness of diffusion models for optical flow and monocular depth estimation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Saxena"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01987"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2003.819861"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00216"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00987"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref56","first-page":"25278","article-title":"LAION-5B: An open large-scale dataset for training next generation image-text models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Schuhmann"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00271"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1017\/S0263574705211621"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/W14-4012"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.264"},{"key":"ref61","first-page":"35","article-title":"Unsupervised scale-consistent depth and ego-motion learning from monocular video","volume-title":"Proc. Adv. Neural Inf. Process. Syst., Annu. Conf. Neural Inf. Process. Syst.","volume":"32","author":"Bian"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/3DV.2018.00073"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2019.00051"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00907"},{"key":"ref65","first-page":"1908","article-title":"Unsupervised monocular depth learning in dynamic scenes","volume-title":"Proc. CoRL","author":"Li"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00482"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00122"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i3.16281"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i6.28383"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72646-0_12"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00172"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01778"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018001"},{"key":"ref74","first-page":"54987","article-title":"Dynamo-depth: Fixing unsupervised depth estimation for dynamical scenes","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Sun"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00877"},{"key":"ref76","author":"von Platen","year":"2024","journal-title":"Diffusers: State-of-the-Art Diffusion Models"},{"key":"ref77","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014","journal-title":"arXiv:1412.6980"},{"key":"ref78","article-title":"Weakly-supervised monocular depth estimationwith resolution-mismatched data","author":"Xu","year":"2021","journal-title":"arXiv:2109.11573"}],"container-title":["IEEE Transactions on Intelligent Transportation Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6979\/11063346\/11021548.pdf?arnumber=11021548","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,3]],"date-time":"2025-07-03T05:12:47Z","timestamp":1751519567000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11021548\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7]]},"references-count":78,"journal-issue":{"issue":"7"},"URL":"https:\/\/doi.org\/10.1109\/tits.2025.3571027","relation":{},"ISSN":["1524-9050","1558-0016"],"issn-type":[{"value":"1524-9050","type":"print"},{"value":"1558-0016","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,7]]}}}