{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,7]],"date-time":"2026-03-07T17:46:39Z","timestamp":1772905599858,"version":"3.50.1"},"reference-count":84,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"9","license":[{"start":{"date-parts":[[2025,9,1]],"date-time":"2025-09-01T00:00:00Z","timestamp":1756684800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,9,1]],"date-time":"2025-09-01T00:00:00Z","timestamp":1756684800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,9,1]],"date-time":"2025-09-01T00:00:00Z","timestamp":1756684800000},"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":"publisher","award":["62227801"],"award-info":[{"award-number":["62227801"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100018537","name":"National Science and Technology Major Project","doi-asserted-by":"crossref","award":["2022ZD0117902"],"award-info":[{"award-number":["2022ZD0117902"]}],"id":[{"id":"10.13039\/501100018537","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Visual. Comput. Graphics"],"published-print":{"date-parts":[[2025,9]]},"DOI":"10.1109\/tvcg.2024.3506992","type":"journal-article","created":{"date-parts":[[2024,11,27]],"date-time":"2024-11-27T14:33:42Z","timestamp":1732718022000},"page":"6280-6292","source":"Crossref","is-referenced-by-count":4,"title":["Isolated Diffusion: Optimizing Multi-Concept Text-to-Image Generation Training-Freely With Isolated Diffusion Guidance"],"prefix":"10.1109","volume":"31","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3995-8382","authenticated-orcid":false,"given":"Jingyuan","family":"Zhu","sequence":"first","affiliation":[{"name":"Department of Electronic Engineering, Tsinghua University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5383-5667","authenticated-orcid":false,"given":"Huimin","family":"Ma","sequence":"additional","affiliation":[{"name":"School of Computer and Communication Engineering, University of Science and Technology Beijing, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2040-7938","authenticated-orcid":false,"given":"Jiansheng","family":"Chen","sequence":"additional","affiliation":[{"name":"School of Computer and Communication Engineering, University of Science and Technology Beijing, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9734-6056","authenticated-orcid":false,"given":"Jian","family":"Yuan","sequence":"additional","affiliation":[{"name":"Department of Electronic Engineering, Tsinghua University, Beijing, China"}]}],"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","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Ho"},{"key":"ref3","first-page":"12 438","article-title":"Improved techniques for training score-based generative models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Song"},{"key":"ref4","first-page":"8780","article-title":"Diffusion models beat GANs on image synthesis","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Dhariwal"},{"key":"ref5","first-page":"8162","article-title":"Improved denoising diffusion probabilistic models","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Nichol"},{"key":"ref6","first-page":"21 696","article-title":"Variational diffusion models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Kingma"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02155"},{"key":"ref8","first-page":"1","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"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00192"},{"key":"ref10","first-page":"15890","article-title":"Mix-of-show: Decentralized low-rank adaptation for multi-concept customization of diffusion models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Gu"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00223"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-025-02498-0"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00582"},{"key":"ref14","first-page":"36479","article-title":"Photorealistic text-to-image diffusion models with deep language understanding","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Saharia"},{"key":"ref15","article-title":"Hierarchical text-conditional image generation with clip latents","author":"Ramesh","year":"2022"},{"key":"ref16","article-title":"Ediffi: Text-to-image diffusion models with an ensemble of expert denoisers","author":"Balaji","year":"2022"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref18","first-page":"1","article-title":"SDXL: Improving latent diffusion models for high-resolution image synthesis","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Podell"},{"key":"ref19","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford"},{"key":"ref20","volume-title":"OpenCLIP","author":"Gabriel Ilharco","year":"2021"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19790-1_26"},{"key":"ref22","first-page":"1","article-title":"Training-free structured diffusion guidance for compositional text-to-image synthesis","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Feng"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/3592116"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP49359.2023.10222616"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/wacv57701.2024.00526"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i5.28204"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00714"},{"key":"ref28","first-page":"1","article-title":"Divide & bind your attention for improved generative semantic nursing","volume-title":"Proc. Brit. Mach. Vis. Conf.","author":"Li"},{"key":"ref29","first-page":"3536","article-title":"Linguistic binding in diffusion models: Enhancing attribute correspondence through attention map alignment","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Rassin"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00860"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.91"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.5555\/2969033.2969125"},{"key":"ref34","first-page":"1","article-title":"Large scale GAN training for high fidelity natural image synthesis","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Brock"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00453"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00813"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2106.12423"},{"key":"ref38","article-title":"Auto-encoding variational bayes","author":"Kingma","year":"2013"},{"key":"ref39","first-page":"1278","article-title":"Stochastic backpropagation and approximate inference in deep generative models","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Rezende"},{"key":"ref40","first-page":"19667","article-title":"Nvae: A deep hierarchical variational autoencoder","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Vahdat"},{"key":"ref41","first-page":"4797","article-title":"Conditional image generation with PixelCNN decoders","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Van den Oord"},{"key":"ref42","first-page":"864","article-title":"Pixelsnail: An improved autoregressive generative model","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Chen"},{"key":"ref43","article-title":"Scaling laws for autoregressive generative modeling","author":"Henighan","year":"2020"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"ref45","article-title":"Uni-controlnet: All-in-one control to text-to-image diffusion models","author":"Zhao","year":"2023"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i5.28226"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02156"},{"key":"ref48","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"},{"key":"ref49","article-title":"Semantic image synthesis via diffusion models","author":"Wang","year":"2022"},{"key":"ref50","first-page":"16222","article-title":"Diffusion self-guidance for controllable image generation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Epstein"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1145\/2897824.2925972"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1145\/3132703"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.1986.4767851"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i1.19953"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01228-1_26"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19784-0_6"},{"key":"ref57","article-title":"Layoutdiffuse: Adapting foundational diffusion models for layout-to-image generation","author":"Cheng","year":"2023"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02154"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01370"},{"key":"ref60","article-title":"Generate anything anywhere in any scene","author":"Li","year":"2023"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00685"},{"key":"ref62","first-page":"1737","article-title":"Multidiffusion: Fusing diffusion paths for controlled image generation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Bar-Tal"},{"key":"ref63","article-title":"Odgen: Domain-specific object detection data generation with diffusion models","author":"Zhu","year":"2024"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00526"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02148"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01117"},{"key":"ref67","article-title":"IPO-LDM: Depth-aided 360-degree indoor RGB panorama outpainting via latent diffusion model","author":"Wu","year":"2023"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3204461"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.00624"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1145\/3641519.3657469"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i2.27824"},{"key":"ref72","article-title":"Paint by word","author":"Bau","year":"2021"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1145\/3592450"},{"key":"ref74","article-title":"Region-aware diffusion for zero-shot text-driven image editing","author":"Huang","year":"2023"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612191"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01764"},{"key":"ref77","first-page":"1","article-title":"Diffedit: Diffusion-based semantic image editing with mask guidance","volume-title":"Proc. 11th Int. Conf. Learn. Representations","author":"Couairon"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01767"},{"key":"ref79","first-page":"68539","article-title":"Toolformer: Language models can teach themselves to use tools","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Schick"},{"key":"ref80","first-page":"5775","article-title":"DPM-solver: A fast ode solver for diffusion probabilistic model sampling in around 10 steps","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Lu"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref82","first-page":"78723","article-title":"T2i-compbench: A comprehensive benchmark for open-world compositional text-to-image generation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Huang"},{"key":"ref83","first-page":"12888","article-title":"Blip: Bootstrapping language-image pre-training for unified vision-language understanding and generation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Li"},{"key":"ref84","article-title":"MiniGPT-4: Enhancing vision-language understanding with advanced large language models","author":"Zhu","year":"2023"}],"container-title":["IEEE Transactions on Visualization and Computer Graphics"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/2945\/11105772\/10769038.pdf?arnumber=10769038","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,5]],"date-time":"2025-08-05T22:06:36Z","timestamp":1754431596000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10769038\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9]]},"references-count":84,"journal-issue":{"issue":"9"},"URL":"https:\/\/doi.org\/10.1109\/tvcg.2024.3506992","relation":{},"ISSN":["1077-2626","1941-0506","2160-9306"],"issn-type":[{"value":"1077-2626","type":"print"},{"value":"1941-0506","type":"electronic"},{"value":"2160-9306","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,9]]}}}