{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,6]],"date-time":"2025-11-06T19:04:59Z","timestamp":1762455899500,"version":"build-2065373602"},"reference-count":60,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2022YFC3303600"],"award-info":[{"award-number":["2022YFC3303600"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100007129","name":"Natural Science Foundation of Shandong Province (Major Basic Research) Project","doi-asserted-by":"publisher","award":["ZR2024ZD12"],"award-info":[{"award-number":["ZR2024ZD12"]}],"id":[{"id":"10.13039\/501100007129","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. on Image Process."],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/tip.2025.3623869","type":"journal-article","created":{"date-parts":[[2025,10,28]],"date-time":"2025-10-28T17:39:39Z","timestamp":1761673179000},"page":"6978-6992","source":"Crossref","is-referenced-by-count":0,"title":["Consistent Image Layout Editing With Diffusion Models"],"prefix":"10.1109","volume":"34","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-5485-7160","authenticated-orcid":false,"given":"Tao","family":"Xia","sequence":"first","affiliation":[{"name":"School of Computer, Beijing Institute of Technology, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-5581-0235","authenticated-orcid":false,"given":"Yudi","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Computer, Beijing Institute of Technology, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ting","family":"Liu","sequence":"additional","affiliation":[{"name":"MT Laboratory, Meitu Inc., Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2286-0314","authenticated-orcid":false,"given":"Lei","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Computer, Beijing Institute of Technology, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","first-page":"16222","article-title":"Diffusion self-guidance for controllable image generation","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NIPS)","author":"Epstein"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref3","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NIPS)","author":"Ho"},{"key":"ref4","first-page":"8821","article-title":"Zero-shot text-to-image generation","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Ramesh"},{"key":"ref5","article-title":"Denoising diffusion implicit models","author":"Song","year":"2020","journal-title":"arXiv:2010.02502"},{"key":"ref6","article-title":"SDXL: Improving latent diffusion models for high-resolution image synthesis","author":"Podell","year":"2023","journal-title":"arXiv:2307.01952"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2025.3539935"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00685"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00207"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00526"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00844"},{"key":"ref13","article-title":"LoRA: Low-rank adaptation of large language models","author":"Hu","year":"2021","journal-title":"arXiv:2106.09685"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02155"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1080\/14786440109462720"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00191"},{"key":"ref17","first-page":"1","article-title":"TokenFlow: Consistent diffusion features for consistent video editing","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Geyer"},{"key":"ref18","article-title":"LAION-400M: Open dataset of CLIP-filtered 400 million image-text pairs","author":"Schuhmann","year":"2021","journal-title":"arXiv:2111.02114"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00356"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02156"},{"key":"ref21","article-title":"ReCo: Region-controlled text-to-image generation","author":"Yang","year":"2022","journal-title":"arXiv:2211.15518"},{"key":"ref22","article-title":"MultiDiffusion: Fusing diffusion paths for controlled image generation","author":"Bar-Tal","year":"2023","journal-title":"arXiv:2302.08113"},{"key":"ref23","article-title":"Cones: Concept neurons in diffusion models for customized generation","author":"Liu","year":"2023","journal-title":"arXiv:2303.05125"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00581"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i5.28204"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.52202\/079017-1868"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00246"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00582"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01764"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3329358"},{"key":"ref31","article-title":"Prompt-to-prompt image editing with cross attention control","author":"Hertz","year":"2022","journal-title":"arXiv:2208.01626"},{"key":"ref32","article-title":"Fine-grained image editing by pixel-wise guidance using diffusion models","author":"Matsunaga","year":"2022","journal-title":"arXiv:2212.02024"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00610"},{"key":"ref34","article-title":"DesignEdit: Multi-layered latent decomposition and fusion for unified & accurate image editing","author":"Jia","year":"2024","journal-title":"arXiv:2403.14487"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1111\/cgf.14966"},{"key":"ref36","first-page":"1363","article-title":"Emergent correspondence from image diffusion","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NIPS)","author":"Tang"},{"key":"ref37","first-page":"1","article-title":"DragonDiffusion: Enabling drag-style manipulation on diffusion models","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Mou"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00774"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02062"},{"key":"ref41","first-page":"1","article-title":"The blessing of randomness: SDE beats ODE in general diffusion-based image editing","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Nie"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00585"},{"key":"ref43","article-title":"Direct inversion: Boosting diffusion-based editing with 3 lines of code","author":"Ju","year":"2023","journal-title":"arXiv:2310.01506"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3089905"},{"key":"ref45","first-page":"1","article-title":"An image is worth one word: Personalizing text-to-image generation using textual inversion","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Gal"},{"key":"ref46","article-title":"Multi-concept customization of text-to-image diffusion","author":"Kumari","year":"2022","journal-title":"arXiv:2212.04488"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1145\/3588432.3591506"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01018"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00121"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01767"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1145\/3592450"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72751-1_15"},{"key":"ref53","article-title":"Grounding DINO 1.5: Advance the \u2019edge\u2019 of open-set object detection","author":"Ren","year":"2024","journal-title":"arXiv:2405.10300"},{"key":"ref54","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Radford"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/WACV51458.2022.00323"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01122"},{"key":"ref58","first-page":"8488","article-title":"DiffEditor: Enhancing speech editing with semantic enrichment and acoustic consistency","volume-title":"Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recognit. (CVPR)","author":"Chen"},{"key":"ref59","article-title":"Scaling rectified flow transformers for high-resolution image synthesis","author":"Esser","year":"2024","journal-title":"arXiv:2403.03206"},{"key":"ref60","article-title":"Demystifying flux architecture","author":"Greenberg","year":"2025","journal-title":"arXiv:2507.09595"}],"container-title":["IEEE Transactions on Image Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/83\/10795784\/11218740.pdf?arnumber=11218740","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,6]],"date-time":"2025-11-06T18:55:26Z","timestamp":1762455326000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11218740\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":60,"URL":"https:\/\/doi.org\/10.1109\/tip.2025.3623869","relation":{},"ISSN":["1057-7149","1941-0042"],"issn-type":[{"type":"print","value":"1057-7149"},{"type":"electronic","value":"1941-0042"}],"subject":[],"published":{"date-parts":[[2025]]}}}