{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,28]],"date-time":"2026-10-28T16:47:40Z","timestamp":1793206060688,"version":"4.5.0"},"reference-count":45,"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":[{"name":"GPU"},{"name":"MCC Lab of USTC"},{"name":"Supercomputing Center of USTC"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/tmm.2026.3680594","type":"journal-article","created":{"date-parts":[[2026,4,6]],"date-time":"2026-04-06T19:57:19Z","timestamp":1775505439000},"page":"9438-9449","source":"Crossref","is-referenced-by-count":3,"title":["Semantic Image Synthesis via Diffusion Models"],"prefix":"10.1109","volume":"28","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1690-9836","authenticated-orcid":false,"given":"Wengang","family":"Zhou","sequence":"first","affiliation":[{"name":"University of Science and Technology of China","place":["Hefei, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0037-4147","authenticated-orcid":false,"given":"Weilun","family":"Wang","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China","place":["Hefei, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-5626-3264","authenticated-orcid":false,"given":"Jianmin","family":"Bao","sequence":"additional","affiliation":[{"name":"Microsoft Research Asia","place":["Beijing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dongdong","family":"Chen","sequence":"additional","affiliation":[{"name":"Microsoft Cloud+AI","place":["Redmond, WA, USA"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0588-9331","authenticated-orcid":false,"given":"Dong","family":"Chen","sequence":"additional","affiliation":[{"name":"Microsoft Research Asia","place":["Beijing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7879-0389","authenticated-orcid":false,"given":"Lu","family":"Yuan","sequence":"additional","affiliation":[{"name":"Microsoft Cloud+AI","place":["Redmond, WA, USA"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2188-3028","authenticated-orcid":false,"given":"Houqiang","family":"Li","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China","place":["Hefei, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","first-page":"570","article-title":"Learning to predict layout-to-image conditional convolutions for semantic image synthesis","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Liu","year":"2019"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00244"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01673-x"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3416270"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00789"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00917"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.5555\/2969033.2969125"},{"key":"ref8","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Ho","year":"2020"},{"key":"ref9","first-page":"8780","article-title":"Diffusion models beat GANs on image synthesis","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Dhariwal","year":"2021"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01043"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3528233.3530757"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3204461"},{"key":"ref13","article-title":"Classifier-free diffusion guidance","volume-title":"Proc. NeurIPSW","author":"Ho","year":"2021"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1714"},{"key":"ref15","first-page":"16784","article-title":"GLIDE: Towards photorealistic image generation and editing with text-guided diffusion models","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Nichol","year":"2022"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.632"},{"key":"ref17","article-title":"SDEdit: Image synthesis and editing with stochastic differential equations","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Meng","year":"2021"},{"key":"ref18","article-title":"Dual diffusion implicit bridges for image-to-image translation","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Su","year":"2022"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01349"},{"key":"ref20","first-page":"465","article-title":"Toward multimodal image-to-image translation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"30","author":"Zhu","year":"2017"},{"key":"ref21","article-title":"Diversity-sensitive conditional generative adversarial networks","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Hong","year":"2019"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00787"},{"key":"ref23","article-title":"Vector-quantized image modeling with improved VQGAN","author":"Yu","year":"2021"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01268"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19787-1_7"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01082"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01370"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00813"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3076487"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00551"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.350"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.544"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00559"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00132"},{"key":"ref36","first-page":"8162","article-title":"Improved denoising diffusion probabilistic models","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Nichol","year":"2021"},{"key":"ref37","article-title":"Decoupled weight decay regularization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Loshchilov","year":"2018"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00068"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.75"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01228-1_26"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1412.7062"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0418"},{"key":"ref44","article-title":"Denoising diffusion implicit models","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Song","year":"2020"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01117"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6046\/11342315\/11474738.pdf?arnumber=11474738","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,10,6]],"date-time":"2026-10-06T19:13:38Z","timestamp":1791314018000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11474738\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":45,"URL":"https:\/\/doi.org\/10.1109\/tmm.2026.3680594","relation":{},"ISSN":["1941-0077","1520-9210"],"issn-type":[{"value":"1941-0077","type":"electronic"},{"value":"1520-9210","type":"print"}],"subject":[],"published":{"date-parts":[[2026]]}}}