{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,28]],"date-time":"2026-01-28T22:32:18Z","timestamp":1769639538308,"version":"3.49.0"},"reference-count":58,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"10","license":[{"start":{"date-parts":[[2024,10,1]],"date-time":"2024-10-01T00:00:00Z","timestamp":1727740800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"funder":[{"name":"Italian Ministry of Enterprises and Made in Italy (Ministero delle Imprese e del Made in Italy - MIMIT) with the project PDMI under the agreements for innovation in the automotive sector","award":["D.M. 31\/12\/2021"],"award-info":[{"award-number":["D.M. 31\/12\/2021"]}]},{"name":"Italian Ministry of Enterprises and Made in Italy (Ministero delle Imprese e del Made in Italy - MIMIT) with the project PDMI under the agreements for innovation in the automotive sector","award":["DD 10\/10\/2022"],"award-info":[{"award-number":["DD 10\/10\/2022"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Circuits Syst. Video Technol."],"published-print":{"date-parts":[[2024,10]]},"DOI":"10.1109\/tcsvt.2024.3404256","type":"journal-article","created":{"date-parts":[[2024,5,22]],"date-time":"2024-05-22T17:46:54Z","timestamp":1716400014000},"page":"9852-9865","source":"Crossref","is-referenced-by-count":7,"title":["D4D: An RGBD Diffusion Model to Boost Monocular Depth Estimation"],"prefix":"10.1109","volume":"34","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9393-5248","authenticated-orcid":false,"given":"Lorenzo","family":"Papa","sequence":"first","affiliation":[{"name":"Department of Computer, Control and Management Engineering, Sapienza University of Rome, Rome, Italy"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1886-3491","authenticated-orcid":false,"given":"Paolo","family":"Russo","sequence":"additional","affiliation":[{"name":"Department of Computer, Control and Management Engineering, Sapienza University of Rome, Rome, Italy"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6461-1391","authenticated-orcid":false,"given":"Irene","family":"Amerini","sequence":"additional","affiliation":[{"name":"Department of Computer, Control and Management Engineering, Sapienza University of Rome, Rome, Italy"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/3042064"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2916648"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.2992393"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/3440207"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1186\/s40537-019-0197-0"},{"key":"ref6","article-title":"Unity: A general platform for intelligent agents","author":"Juliani","year":"2018","journal-title":"arXiv:1809.02627"},{"key":"ref7","volume-title":"Unreal Engine","year":"2023"},{"key":"ref8","first-page":"101","article-title":"MLReal: Bridging the gap between training on synthetic data and real data applications in machine learning","volume":"3","author":"Alkhalifah","year":"2022","journal-title":"Artificial Intell. Geosci."},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8202133"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2018.00143"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2022.103489"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-33715-4_54"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6248074"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref16","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Ho"},{"key":"ref17","first-page":"2256","article-title":"Deep unsupervised learning using nonequilibrium thermodynamics","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Sohl-Dickstein"},{"key":"ref18","article-title":"Diffusion models: A comprehensive survey of methods and applications","author":"Yang","year":"2022","journal-title":"arXiv:2209.00796"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2020.12.089"},{"key":"ref20","article-title":"High quality monocular depth estimation via transfer learning","author":"Alhashim","year":"2018","journal-title":"arXiv:1812.11941"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8794182"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2022.3170425"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/tcsvt.2023.3260310"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-51023-6_32"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.292"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.352"},{"key":"ref27","article-title":"DIML\/CVL RGB-D dataset: 2M RGB-D images of natural indoor and outdoor scenes","author":"Cho","year":"2021","journal-title":"arXiv:2110.11590"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00595"},{"key":"ref29","first-page":"12104","article-title":"Training generative adversarial networks with limited data","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Karras"},{"key":"ref30","doi-asserted-by":"crossref","DOI":"10.1016\/j.trc.2020.102697","article-title":"Real-time crash prediction on expressways using deep generative models","volume":"117","author":"Cai","year":"2020","journal-title":"Transp. Res. C, Emerg. Technol."},{"key":"ref31","first-page":"18367","article-title":"Improved transformer for high-resolution GANs","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Zhao"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.244"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00845"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3105725"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00077"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01211"},{"key":"ref37","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":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref39","article-title":"Scalable diffusion models with transformers","author":"Peebles","year":"2022","journal-title":"arXiv:2212.09748"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref41","volume-title":"NVIDIA, Isaac Sim","year":"2023"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01228-1_3"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00575"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00069"},{"key":"ref45","first-page":"8162","article-title":"Improved denoising diffusion probabilistic models","volume-title":"Proc. 38th Int. Conf. Mach. Learn.","author":"Nichol"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2019.00116"},{"key":"ref47","article-title":"PyTorch: An imperative style, high-performance deep learning library","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Paszke"},{"key":"ref48","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":"ref49","article-title":"Micro-batch training with batch-channel normalization and weight standardization","author":"Qiao","year":"2019","journal-title":"arXiv:1903.10520"},{"key":"ref50","article-title":"Decoupled weight decay regularization","author":"Loshchilov","year":"2017","journal-title":"arXiv:1711.05101"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01055"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00061"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref54","first-page":"6105","article-title":"EfficientNet: Rethinking model scaling for convolutional neural networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Tan"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511811555"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.161"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3194350"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3180274"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/76\/10739869\/10536915.pdf?arnumber=10536915","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,27]],"date-time":"2024-11-27T00:21:13Z","timestamp":1732666873000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10536915\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10]]},"references-count":58,"journal-issue":{"issue":"10"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2024.3404256","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,10]]}}}