{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,15]],"date-time":"2026-06-15T18:40:56Z","timestamp":1781548856230,"version":"3.54.5"},"reference-count":97,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"4","license":[{"start":{"date-parts":[[2025,4,1]],"date-time":"2025-04-01T00:00:00Z","timestamp":1743465600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,4,1]],"date-time":"2025-04-01T00:00:00Z","timestamp":1743465600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,4,1]],"date-time":"2025-04-01T00:00:00Z","timestamp":1743465600000},"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":["62333023"],"award-info":[{"award-number":["62333023"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"Agency for Science, Technology and Research (A*STAR)- Manufacturing, Trade and Connectivity (MTC) Programmatic Funds","doi-asserted-by":"publisher","award":["M23L7b0021"],"award-info":[{"award-number":["M23L7b0021"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100022963","name":"key Research and Development Program of Zhejiang Province","doi-asserted-by":"publisher","award":["2024C03042"],"award-info":[{"award-number":["2024C03042"]}],"id":[{"id":"10.13039\/100022963","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100022963","name":"key Research and Development Program of Zhejiang Province","doi-asserted-by":"publisher","award":["2021C03050"],"award-info":[{"award-number":["2021C03050"]}],"id":[{"id":"10.13039\/100022963","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61620106012"],"award-info":[{"award-number":["61620106012"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Circuits Syst. Video Technol."],"published-print":{"date-parts":[[2025,4]]},"DOI":"10.1109\/tcsvt.2024.3509619","type":"journal-article","created":{"date-parts":[[2024,12,2]],"date-time":"2024-12-02T18:43:26Z","timestamp":1733165006000},"page":"3664-3678","source":"Crossref","is-referenced-by-count":22,"title":["MonoDiffusion: Self-Supervised Monocular Depth Estimation Using Diffusion Model"],"prefix":"10.1109","volume":"35","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8057-1599","authenticated-orcid":false,"given":"Shuwei","family":"Shao","sequence":"first","affiliation":[{"name":"School of Automation Science and Electrical Engineering, Beihang University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7748-8591","authenticated-orcid":false,"given":"Zhongcai","family":"Pei","sequence":"additional","affiliation":[{"name":"School of Automation Science and Electrical Engineering, Beihang University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7912-4505","authenticated-orcid":false,"given":"Weihai","family":"Chen","sequence":"additional","affiliation":[{"name":"School of Automation Science and Electrical Engineering, Beihang University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dingchi","family":"Sun","sequence":"additional","affiliation":[{"name":"School of Automation Science and Electrical Engineering, Beihang University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4851-9875","authenticated-orcid":false,"given":"Peter C. Y.","family":"Chen","sequence":"additional","affiliation":[{"name":"Department of Mechanical Engineering, National University of Singapore, Cluny Road, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4525-1204","authenticated-orcid":false,"given":"Zhengguo","family":"Li","sequence":"additional","affiliation":[{"name":"VI Department, Institute for Infocomm Research, A*STAR, Fusionopolis, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/2047196.2047270"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00273"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2022.3185303"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1080\/23307706.2022.2065370"},{"key":"ref5","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.","volume":"27","author":"Eigen"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.700"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02052"},{"key":"ref8","article-title":"From big to small: Multi-scale local planar guidance for monocular depth estimation","author":"Han Lee","year":"2019","journal-title":"arXiv:1907.10326"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00400"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2836318"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00578"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3049869"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3072215"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3080928"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01527"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01228-1_3"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00393"},{"key":"ref18","first-page":"1","article-title":"Unsupervised scale-consistent depth and ego-motion learning from monocular video","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Bian"},{"key":"ref19","article-title":"Unsupervised learning of geometry with edge-aware depth-normal consistency","author":"Yang","year":"2017","journal-title":"arXiv:1711.03665"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3275584"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00481"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01441"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01241"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58565-5_35"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01778"},{"key":"ref26","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Ho"},{"key":"ref27","first-page":"1","article-title":"Denoising diffusion implicit models","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Song"},{"key":"ref28","first-page":"1","article-title":"Generative modeling by estimating gradients of the data distribution","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Song"},{"key":"ref29","first-page":"1","article-title":"Score-based generative modeling through stochastic differential equations","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Song"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00813"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1145\/3528233.3530757"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i2.25313"},{"key":"ref34","article-title":"GLIDE: Towards photorealistic image generation and editing with text-guided diffusion models","author":"Nichol","year":"2021","journal-title":"arXiv:2112.10741"},{"key":"ref35","first-page":"36479","article-title":"Photorealistic text-to-image diffusion models with deep language understanding","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Saharia"},{"key":"ref36","article-title":"Hierarchical text-conditional image generation with CLIP latents","author":"Ramesh","year":"2022","journal-title":"arXiv:2204.06125"},{"key":"ref37","first-page":"144","article-title":"DiffFAS: Face anti-spoofing via generative diffusion models","volume-title":"Proc. Eur. Conf. Comput. Vis.","author":"Ge"},{"key":"ref38","first-page":"1","article-title":"Diffusion model for dense matching","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Nam"},{"key":"ref39","first-page":"1","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":"ref40","article-title":"Human motion diffusion model","author":"Tevet","year":"2022","journal-title":"arXiv:2209.14916"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01464"},{"key":"ref42","article-title":"SegDiff: Image segmentation with diffusion probabilistic models","author":"Amit","year":"2021","journal-title":"arXiv:2112.00390"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00090"},{"key":"ref44","first-page":"1623","article-title":"MedSegdiff: Medical image segmentation with diffusion probabilistic model","volume-title":"Proc. Med. Imag. Deep Learn.","author":"Wu"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01987"},{"key":"ref46","article-title":"Monocular depth estimation using diffusion models","author":"Saxena","year":"2023","journal-title":"arXiv:2302.14816"},{"key":"ref47","article-title":"DiffusionDepth: Diffusion denoising approach for monocular depth estimation","author":"Duan","year":"2023","journal-title":"arXiv:2303.05021"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00907"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72670-5_14"},{"key":"ref50","article-title":"DepthFM: Fast monocular depth estimation with flow matching","author":"Gui","year":"2024","journal-title":"arXiv:2403.13788"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6248074"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2008.132"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/3DV.2016.32"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2017.2740321"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00214"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00389"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3310259"},{"key":"ref59","first-page":"1","article-title":"VA-depthnet: A variational approach to single image depth prediction","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Liu"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00729"},{"key":"ref61","article-title":"ZoeDepth: Zero-shot transfer by combining relative and metric depth","author":"Farooq Bhat","year":"2023","journal-title":"arXiv:2302.12288"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01250"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01094"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00256"},{"key":"ref65","first-page":"1","article-title":"Semantically-guided representation learning for self-supervised monocular depth","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Guizilini"},{"key":"ref66","first-page":"2256","article-title":"Deep unsupervised learning using nonequilibrium thermodynamics","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Sohl-Dickstein"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01764"},{"issue":"47","key":"ref68","first-page":"1","article-title":"Cascaded diffusion models for high fidelity image generation","volume":"23","author":"Ho","year":"2022","journal-title":"J. Mach. Learn. Res."},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3204461"},{"key":"ref70","article-title":"Pyramidal denoising diffusion probabilistic models","author":"Ryu","year":"2022","journal-title":"arXiv:2208.01864"},{"key":"ref71","first-page":"1336","article-title":"Diffusion models for implicit image segmentation ensembles","volume-title":"Proc. Int. Conf. Med. Imag. With Deep Learn.","author":"Wolleb"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW56347.2022.00462"},{"key":"ref73","first-page":"1","article-title":"Label-efficient semantic segmentation with diffusion models","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Baranchuk"},{"key":"ref74","article-title":"DiffusionDet: Diffusion model for object detection","author":"Chen","year":"2022","journal-title":"arXiv:2211.09788"},{"key":"ref75","first-page":"8780","article-title":"Diffusion models beat gans on image synthesis","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Dhariwal"},{"key":"ref76","article-title":"Conditional image generation with score-based diffusion models","author":"Batzolis","year":"2021","journal-title":"arXiv:2111.13606"},{"key":"ref77","first-page":"1","article-title":"Spatial transformer networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"28","author":"Jaderberg"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr42600.2020.00136"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2003.819861"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01492"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00212"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00216"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/3DV53792.2021.00056"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i3.16329"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01254"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i1.25090"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1109\/3DV57658.2022.00077"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1109\/3DV.2017.00012"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01252"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2930258"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.699"},{"key":"ref94","first-page":"1","article-title":"Decoupled weight decay regularization","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Loshchilov"},{"key":"ref95","first-page":"1","article-title":"SGDR: Stochastic gradient descent with warm restarts","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Loshchilov"},{"key":"ref96","first-page":"1","article-title":"Benchmarking neural network robustness to common corruptions and perturbations","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Hendrycks"},{"key":"ref97","article-title":"Global-local path networks for monocular depth estimation with vertical CutDepth","author":"Kim","year":"2022","journal-title":"arXiv:2201.07436"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/76\/10949577\/10772032.pdf?arnumber=10772032","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,4,7]],"date-time":"2025-04-07T22:13:20Z","timestamp":1744064000000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10772032\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4]]},"references-count":97,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2024.3509619","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,4]]}}}