{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,23]],"date-time":"2026-02-23T21:29:37Z","timestamp":1771882177684,"version":"3.50.1"},"reference-count":46,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/access.2026.3651731","type":"journal-article","created":{"date-parts":[[2026,1,12]],"date-time":"2026-01-12T22:02:28Z","timestamp":1768255348000},"page":"26953-26964","source":"Crossref","is-referenced-by-count":0,"title":["UDepthDiff: Multi-Modal Physical Diffusion-Based Underwater Monocular Depth Estimation"],"prefix":"10.1109","volume":"14","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-3894-2230","authenticated-orcid":false,"given":"Hengbin","family":"Zhu","sequence":"first","affiliation":[{"name":"School of Mathematics and Statistics, Ningbo University, Ningbo, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zexuan","family":"Xing","sequence":"additional","affiliation":[{"name":"Honors College, Ningbo University of Finance and Economics, Ningbo, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10161439"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.displa.2025.103132"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.displa.2025.103125"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2023.3318629"},{"issue":"4","key":"ref5","first-page":"81","article-title":"Research status and progress of binocular stereo vision","volume":"40","author":"Huang","year":"2018","journal-title":"Opt. Instrum."},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TCI.2021.3111572"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2016.2612882"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2019.8804200"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00907"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681168"},{"key":"ref11","article-title":"SFM-Net: Learning of structure and motion from video","author":"Vijayanarasimhan","year":"2017","journal-title":"arXiv:1704.07804"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.699"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/34.784284"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1023\/A:1007958829620"},{"key":"ref15","first-page":"2197","article-title":"Depth estimation using monocular and stereo cues","volume-title":"Proc. IJCAI","author":"Saxena"},{"key":"ref16","first-page":"1","article-title":"Depth map prediction from a single image using a multi-scale deep network","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Eigen"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00214"},{"key":"ref18","article-title":"ZoeDepth: Zero-shot transfer by combining relative and metric depth","author":"Bhat","year":"2023","journal-title":"arXiv:2302.12288"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-025-96024-4"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01196"},{"key":"ref21","article-title":"Iris: Integrating language into diffusion-based monocular depth estimation","author":"Zeng","year":"2024","journal-title":"arXiv:2411.16750"},{"key":"ref22","article-title":"DICEPTION: A generalist diffusion model for visual perceptual tasks","author":"Zhao","year":"2025","journal-title":"arXiv:2502.17157"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2025.3545595"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1016\/j.procs.2025.04.531"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3310259"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00716"},{"key":"ref27","article-title":"BinsFormer: Revisiting adaptive bins for monocular depth estimation","author":"Li","year":"2022","journal-title":"arXiv:2204.00987"},{"key":"ref28","article-title":"A practical approach to underwater depth and surface normals estimation","author":"Saleh","year":"2024","journal-title":"arXiv:2410.02072"},{"key":"ref29","article-title":"UDepth: Fast monocular depth estimation for visually-guided underwater robots","author":"Yu","year":"2022","journal-title":"arXiv:2209.12358"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2024.3373904"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73337-6_14"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2023.127122"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/MCG.2016.26"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2010.168"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref36","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Ho"},{"key":"ref37","first-page":"8162","article-title":"Improved denoising diffusion probabilistic models","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Nichol"},{"key":"ref38","article-title":"Denoising diffusion implicit models","author":"Song","year":"2020","journal-title":"arXiv:2010.02502"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00090"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/WACVW54805.2022.00072"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3266163"},{"key":"ref42","article-title":"Flsea: Underwater visual-inertial and stereo-vision forward-looking datasets","author":"Randall","year":"2023"},{"key":"ref43","article-title":"Very deep convolutional networks for large-scale image recognition","author":"Simonyan","year":"2014","journal-title":"arXiv:1409.1556"},{"key":"ref44","article-title":"High quality monocular depth estimation via transfer learning","author":"Alhashim","year":"2018","journal-title":"arXiv:1812.11941"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00581"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01778"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6287639\/11323511\/11339494.pdf?arnumber=11339494","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,23]],"date-time":"2026-02-23T20:49:48Z","timestamp":1771879788000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11339494\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":46,"URL":"https:\/\/doi.org\/10.1109\/access.2026.3651731","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}