{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,7]],"date-time":"2026-04-07T21:09:29Z","timestamp":1775596169976,"version":"3.50.1"},"reference-count":50,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"4","license":[{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100012226","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":[[2026,4]]},"DOI":"10.1109\/tcsvt.2025.3626857","type":"journal-article","created":{"date-parts":[[2025,10,30]],"date-time":"2025-10-30T18:04:15Z","timestamp":1761847455000},"page":"4492-4504","source":"Crossref","is-referenced-by-count":0,"title":["Draw Like an Artist: Complex Scene Generation With Diffusion Model via Composition, Painting, and Retouching"],"prefix":"10.1109","volume":"36","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-1660-9379","authenticated-orcid":false,"given":"Minghao","family":"Liu","sequence":"first","affiliation":[{"name":"School of Computer Science and Technology, University of Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-1556-8165","authenticated-orcid":false,"given":"Le","family":"Zhang","sequence":"additional","affiliation":[{"name":"MT Lab, Meitu Inc., Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4675-0398","authenticated-orcid":false,"given":"Yingjie","family":"Tian","sequence":"additional","affiliation":[{"name":"School of Economics and Management, University of Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaochao","family":"Qu","sequence":"additional","affiliation":[{"name":"MT Lab, Meitu Inc., Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-6607-4072","authenticated-orcid":false,"given":"Luoqi","family":"Liu","sequence":"additional","affiliation":[{"name":"MT Lab, Meitu Inc., Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-7988-5935","authenticated-orcid":false,"given":"Ting","family":"Liu","sequence":"additional","affiliation":[{"name":"MT Lab, Meitu Inc., Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","first-page":"2256","article-title":"Deep unsupervised learning using nonequilibrium thermodynamics","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Sohl-Dickstein"},{"key":"ref2","article-title":"Score-based generative modeling through stochastic differential equations","author":"Song","year":"2020","journal-title":"arXiv:2011.13456"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/3626235"},{"key":"ref4","article-title":"High-resolution complex scene synthesis with transformers","author":"Jahn","year":"2021","journal-title":"arXiv:2105.06458"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02156"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00685"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612012"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00526"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02072"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00708"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i6.28364"},{"key":"ref12","article-title":"Mastering text-to-image diffusion: Recaptioning, planning, and generating with multimodal LLMs","volume-title":"Proc. 41st Int. Conf. Mach. Learn.","author":"Yang"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1525\/9780520351271"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.2307\/jj.8441755"},{"key":"ref15","volume-title":"The Story of Art","volume":"12","author":"Gombrich","year":"1995"},{"key":"ref16","doi-asserted-by":"crossref","DOI":"10.2307\/jj.7013084","volume-title":"Art of the Modern Age:Philosophy of Art from Kant to Heidegger","author":"Schaeffer","year":"2023"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00605"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00761"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-658-40442-0_9"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3294261"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3347971"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3298811"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2023.3270561"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i2.16250"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00083"},{"key":"ref27","first-page":"8780","article-title":"Diffusion models beat GANs on image synthesis","volume-title":"Proc. NIPS","volume":"34","author":"Dhariwal"},{"key":"ref28","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume-title":"Proc. NIPS","volume":"33","author":"Ho"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01369"},{"key":"ref31","article-title":"Composer: Creative and controllable image synthesis with composable conditions","author":"Huang","year":"2023","journal-title":"arXiv:2302.09778"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i5.28226"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19790-1_26"},{"key":"ref34","article-title":"MultiDiffusion: Fusing diffusion paths for controlled image generation","author":"Bar-Tal","year":"2023","journal-title":"arXiv:2302.08113"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/JAS.2023.123618"},{"key":"ref36","article-title":"Kosmos-G: Generating images in context with multimodal large language models","author":"Pan","year":"2023","journal-title":"arXiv:2310.02992"},{"key":"ref37","first-page":"6048","article-title":"Visual programming for step-by-step text-to-image generation and evaluation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Cho"},{"key":"ref38","article-title":"LLM-grounded diffusion: Enhancing prompt understanding of text-to-image diffusion models with large language models","author":"Lian","year":"2023","journal-title":"arXiv:2305.13655"},{"key":"ref39","first-page":"18225","article-title":"LayoutGPT: Compositional visual planning and generation with large language models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Feng"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00454"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0981-7"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.52202\/075280-3443"},{"key":"ref43","article-title":"GPT-4 technical report","volume-title":"arXiv:2303.08774","author":"Achiam","year":"2023"},{"key":"ref44","article-title":"Training-free structured diffusion guidance for compositional text-to-image synthesis","author":"Feng","year":"2022","journal-title":"arXiv:2212.05032"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1145\/3592116"},{"key":"ref46","article-title":"Hierarchical text-conditional image generation with CLIP latents","author":"Ramesh","year":"2022","journal-title":"arXiv:2204.06125"},{"key":"ref47","article-title":"SDXL: Improving latent diffusion models for high-resolution image synthesis","author":"Podell","year":"2023","journal-title":"arXiv:2307.01952"},{"key":"ref48","article-title":"PixArt-\u03b1: Fast training of diffusion transformer for photorealistic text-to-image synthesis","author":"Chen","year":"2023","journal-title":"arXiv:2310.00426"},{"key":"ref49","first-page":"37636","article-title":"Improving diffusion-based image synthesis with context prediction","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Yang"},{"key":"ref50","article-title":"Llama 2: Open foundation and fine-tuned chat models","author":"Touvron","year":"2023","journal-title":"arXiv:2307.09288"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/76\/11475579\/11222733.pdf?arnumber=11222733","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,7]],"date-time":"2026-04-07T20:02:57Z","timestamp":1775592177000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11222733\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4]]},"references-count":50,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2025.3626857","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,4]]}}}