{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,15]],"date-time":"2026-10-15T16:22:33Z","timestamp":1792081353652,"version":"4.4.0"},"reference-count":56,"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:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"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":"crossref","award":["62425114"],"award-info":[{"award-number":["62425114"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"name":"Beijing Municipal Science and Technology","award":["Z241100001324002"],"award-info":[{"award-number":["Z241100001324002"]}]},{"DOI":"10.13039\/501100005090","name":"Beijing Nova Program","doi-asserted-by":"crossref","award":["20240484681"],"award-info":[{"award-number":["20240484681"]}],"id":[{"id":"10.13039\/501100005090","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/tmm.2026.3668607","type":"journal-article","created":{"date-parts":[[2026,2,27]],"date-time":"2026-02-27T20:50:03Z","timestamp":1772225403000},"page":"6463-6475","source":"Crossref","is-referenced-by-count":2,"title":["HiFi3D: Improving Text-to-3D With High-Fidelity Multi-View Diffusion"],"prefix":"10.1109","volume":"28","author":[{"given":"Runxin","family":"Liu","sequence":"first","affiliation":[{"name":"University of Science and Technology of China","place":["Hefei, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yang","family":"Chen","sequence":"additional","affiliation":[{"name":"HiDream.ai","place":["Beijing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4344-8898","authenticated-orcid":false,"given":"Yingwei","family":"Pan","sequence":"additional","affiliation":[{"name":"HiDream.ai","place":["Beijing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6249-5315","authenticated-orcid":false,"given":"Hongtao","family":"Xie","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China","place":["Hefei, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1151-1792","authenticated-orcid":false,"given":"Yongdong","family":"Zhang","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China","place":["Hefei, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7587-101X","authenticated-orcid":false,"given":"Ting","family":"Yao","sequence":"additional","affiliation":[{"name":"HiDream.ai","place":["Beijing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2497-7732","authenticated-orcid":false,"given":"Tao","family":"Mei","sequence":"additional","affiliation":[{"name":"HiDream.ai","place":["Beijing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Hierarchical text-conditional image generation with clip latents","author":"Ramesh","year":"2022"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2643"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/3746027.3756870"},{"key":"ref5","article-title":"Make-a-video: Text-to-video generation without text-video data","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Singer","year":"2023"},{"key":"ref6","article-title":"Imagen video: High definition video generation with diffusion models","author":"Ho","year":"2022"},{"key":"ref7","article-title":"Latent video diffusion models for high-fidelity video generation with arbitrary lengths","author":"He","year":"2022"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00175"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1833"},{"key":"ref10","first-page":"2256","article-title":"Deep unsupervised learning using nonequilibrium thermodynamics","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Sohl-Dickstein","year":"2015"},{"key":"ref11","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Ho","year":"2020"},{"key":"ref12","first-page":"8162","article-title":"Improved denoising diffusion probabilistic models","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Nichol","year":"2021"},{"key":"ref13","article-title":"Classifier-free diffusion guidance","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst. Workshop","author":"Ho","year":"2022"},{"key":"ref14","article-title":"Dreamfusion: Text-to-3D using 2D diffusion","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Poole","year":"2023"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_24"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00037"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73202-7_10"},{"key":"ref18","article-title":"Dreamtime: An improved optimization strategy for text-to-3D content creation","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Huang","year":"2023"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0368"},{"key":"ref20","article-title":"Text-to-3D with classifier score distillation","volume-title":"Proc. 12th Int. Conf. Learn. Representations","author":"Yu","year":"2024"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612363"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612489"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00468"},{"key":"ref24","article-title":"MVDream: Multi-view diffusion for 3D generation","volume-title":"Proc. 12th Int. Conf. Learn. Representations","author":"Shi","year":"2024"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00956"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3224327"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.3023339"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3090595"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3160297"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3350937"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2026.3651030"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681634"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3350593"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612678"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3251697"},{"key":"ref37","article-title":"Re-imagine the negative prompt algorithm: Transform 2D diffusion into 3D, alleviate janus problem and beyond","author":"Armandpour","year":"2023"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0523"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00863"},{"key":"ref40","article-title":"An image is worth one word: Personalizing text-to-image generation using textual inversion","volume-title":"Proc. 11th Int. Conf. Learn. Representations","author":"Gal","year":"2023"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02155"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2024.3399075"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01461"},{"key":"ref44","article-title":"IP-adapter: Text compatible image prompt adapter for text-to-image diffusion models","author":"Ye","year":"2023"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.3037461"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00701"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM59182.2024.00036"},{"key":"ref48","article-title":"T$^{3}$ bench: Benchmarking current progress in text-to-3D generation","author":"He","year":"2023"},{"key":"ref49","article-title":"Threestudio: A unified framework for 3D content generation","author":"Guo","year":"2023"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01214"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02033"},{"key":"ref52","article-title":"DreamGaussian: Generative Gaussian splatting for efficient 3D content creation","volume-title":"Proc. 12th Int. Conf. Learn. Representations","author":"Tang","year":"2023"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00946"},{"key":"ref54","article-title":"Geodream: Disentangling 2D and geometric priors for high-fidelity and consistent 3D generation","author":"Ma","year":"2023"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72784-9_8"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01218"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6046\/11342315\/11417239.pdf?arnumber=11417239","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,3]],"date-time":"2026-08-03T19:04:04Z","timestamp":1785783844000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11417239\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":56,"URL":"https:\/\/doi.org\/10.1109\/tmm.2026.3668607","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}