{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,3]],"date-time":"2026-01-03T22:55:00Z","timestamp":1767480900093,"version":"3.41.2"},"reference-count":81,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"8","license":[{"start":{"date-parts":[[2025,8,1]],"date-time":"2025-08-01T00:00:00Z","timestamp":1754006400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,8,1]],"date-time":"2025-08-01T00:00:00Z","timestamp":1754006400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,8,1]],"date-time":"2025-08-01T00:00:00Z","timestamp":1754006400000},"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":["624B2124","62441615","62201484"],"award-info":[{"award-number":["624B2124","62441615","62201484"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2025,8]]},"DOI":"10.1109\/tpami.2025.3562237","type":"journal-article","created":{"date-parts":[[2025,4,25]],"date-time":"2025-04-25T17:40:20Z","timestamp":1745602820000},"page":"6480-6495","source":"Crossref","is-referenced-by-count":1,"title":["AnyDoor: Zero-Shot Image Customization With Region-to-Region Reference"],"prefix":"10.1109","volume":"47","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-5008-4720","authenticated-orcid":false,"given":"Xi","family":"Chen","sequence":"first","affiliation":[{"name":"Department of Computer Science, The University of Hong Kong, Hong Kong"}]},{"given":"Lianghua","family":"Huang","sequence":"additional","affiliation":[{"name":"Alibaba Group, Hangzhou, China"}]},{"given":"Yu","family":"Liu","sequence":"additional","affiliation":[{"name":"Alibaba Group, Hangzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3801-6705","authenticated-orcid":false,"given":"Yujun","family":"Shen","sequence":"additional","affiliation":[{"name":"Ant Group, Hangzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8838-578X","authenticated-orcid":false,"given":"Deli","family":"Zhao","sequence":"additional","affiliation":[{"name":"Alibaba Group, Hangzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8277-2706","authenticated-orcid":false,"given":"Hengshuang","family":"Zhao","sequence":"additional","affiliation":[{"name":"Department of Computer Science, The University of Hong Kong, Hong Kong"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref2","first-page":"36479","article-title":"Photorealistic text-to-image diffusion models with deep language understanding","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Saharia"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"ref4","first-page":"13753","article-title":"Composer: Creative and controllable image synthesis with composable conditions","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Huang"},{"article-title":"Hierarchical text-conditional image generation with clip latents","year":"2022","author":"Ramesh","key":"ref5"},{"key":"ref6","first-page":"42961","article-title":"UniControl: A unified diffusion model for controllable visual generation in the wild","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Qin"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00582"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02062"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00584"},{"article-title":"Inpaint anything: Segment anything meets image inpainting","year":"2023","author":"Yu","key":"ref10"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02148"},{"article-title":"Glide: Towards photorealistic image generation and editing with text-guided diffusion models","year":"2021","author":"Nichol","key":"ref12"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01763"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01756"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02155"},{"article-title":"An image is worth one word: Personalizing text-to-image generation using textual inversion","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Gal","key":"ref16"},{"key":"ref17","first-page":"21548","article-title":"Cones: Concept neurons in diffusion models for customized generation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Liu"},{"key":"ref18","first-page":"57500","article-title":"Cones 2: Customizable image synthesis with multiple subjects","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Liu"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00192"},{"key":"ref20","first-page":"15890","article-title":"Mix-of-show: Decentralized low-rank adaptation for multi-concept customization of diffusion models","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Gu"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/3610548.3618154"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00630"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01767"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref25","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford"},{"article-title":"DisenBooth: Disentangled parameter-efficient tuning for subject-driven text-to-image generation","year":"2023","author":"Chen","key":"ref26"},{"key":"ref27","first-page":"30146","article-title":"Blip-diffusion: Pre-trained subject representation for controllable text-to-image generation and editing","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Li"},{"key":"ref28","first-page":"19730","article-title":"BLIP-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Li"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-024-02227-z"},{"article-title":"IP-adapter: Text compatible image prompt adapter for text-to-image diffusion models","year":"2023","author":"Ye","key":"ref30"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681396"},{"article-title":"DreamEdit: Subject-driven image editing","year":"2023","author":"Li","key":"ref32"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/1833349.1778862"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00842"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00861"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01610"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20071-7_18"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01792"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611747"},{"article-title":"ControlCom: Controllable image composition using diffusion model","year":"2023","author":"Zhang","key":"ref40"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2024\/840"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00853"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2020.107404"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00136"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00725"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02037"},{"key":"ref47","first-page":"1","article-title":"DINOv2: Learning robust visual features without supervision","volume":"2024","author":"Oquab","year":"2024","journal-title":"Trans. Mach. Learn. Res. J."},{"article-title":"Controllable image generation via collage representations","year":"2023","author":"Casanova","key":"ref48"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00416"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/4.996"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01228-1_36"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00529"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01060"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01850"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.02036"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00172"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00883"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01391"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3350946"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2015.2487833"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.404"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00550"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72649-1_27"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2003.819861"},{"article-title":"Graphit: A unified framework for diverse image editing tasks","year":"2023","author":"Contributors","key":"ref65"},{"article-title":"Adam: A method for stochastic optimization","year":"2014","author":"Kingma","key":"ref66"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.00816"},{"key":"ref69","first-page":"30286","article-title":"Subject-driven text-to-image generation via apprenticeship learning","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Chen"},{"key":"ref70","first-page":"6629","article-title":"GANs trained by a two-time-scale update rule converge to a local nash equilibrium","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Heusel"},{"article-title":"Very deep convolutional networks for large-scale image recognition","year":"2014","author":"Simonyan","key":"ref71"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19790-1_13"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02255"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.00781"},{"article-title":"SDXL: Improving latent diffusion models for high-resolution image synthesis","year":"2023","author":"Podell","key":"ref75"},{"article-title":"CLIPAway: Harmonizing focused embeddings for removing objects via diffusion models","year":"2024","author":"Ekin","key":"ref76"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/WACV51458.2022.00323"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73636-0_12"},{"article-title":"Experiments with stable diffusion","year":"2023","author":"Pinkney","key":"ref79"},{"key":"ref80","first-page":"30641","article-title":"Real-world image variation by aligning diffusion inversion chain","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Zhang"},{"key":"ref81","first-page":"84010","article-title":"Zero-shot image editing with reference imitation","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Chen"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/34\/11068886\/10976616.pdf?arnumber=10976616","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,7]],"date-time":"2025-07-07T22:57:13Z","timestamp":1751929033000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10976616\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8]]},"references-count":81,"journal-issue":{"issue":"8"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2025.3562237","relation":{},"ISSN":["0162-8828","2160-9292","1939-3539"],"issn-type":[{"type":"print","value":"0162-8828"},{"type":"electronic","value":"2160-9292"},{"type":"electronic","value":"1939-3539"}],"subject":[],"published":{"date-parts":[[2025,8]]}}}