{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T03:30:49Z","timestamp":1777865449368,"version":"3.51.4"},"reference-count":73,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.01564","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"16840-16850","source":"Crossref","is-referenced-by-count":0,"title":["AIcomposer: Any Style and Content Image Composition via Feature Integration"],"prefix":"10.1109","author":[{"given":"Haowen","family":"Li","sequence":"first","affiliation":[{"name":"Peking University,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhenfeng","family":"Fan","sequence":"additional","affiliation":[{"name":"Beijing Yuanli Science and Technology Co., Ltd.,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhang","family":"Wen","sequence":"additional","affiliation":[{"name":"Beijing Yuanli Science and Technology Co., Ltd.,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhengzhou","family":"Zhu","sequence":"additional","affiliation":[{"name":"Peking University,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yunjin","family":"Li","sequence":"additional","affiliation":[{"name":"Beijing Yuanli Science and Technology Co., Ltd.,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01767"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3592450"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00789"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00861"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00630"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72643-9_5"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1111\/j.1469-1809.1936.tb02137.x"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72684-2_11"},{"key":"ref9","article-title":"An image is worth one word: Personalizing text-to-image generation using textual inversion","author":"Gal","year":"2023","journal-title":"ICLR"},{"key":"ref10","first-page":"262","article-title":"Texture synthesis using convolutional neural networks","volume-title":"NeurIPS","author":"Gatys","year":"2015"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1167\/16.12.326"},{"key":"ref12","author":"Griffin","year":"2023","journal-title":"Caltech-256 object category dataset"},{"key":"ref13","first-page":"6840","article-title":"Denoising diffusion probabilistic models","author":"Ho","year":"2020","journal-title":"NeurIPS"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01462"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.167"},{"key":"ref16","article-title":"Designedit: Multilayered latent decomposition and fusion for unified & accurate image editing","volume":"abs\/2403.14487","author":"Jia","year":"2024","journal-title":"CoRR"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72661-3_9"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00582"},{"key":"ref19","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2015","journal-title":"ICLR"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00192"},{"key":"ref22","article-title":"Blip-diffusion: Pre-trained subject representation for controllable text-toimage generation and editing","author":"Li","year":"2023","journal-title":"NeurIPS"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/3610543.3626172"},{"key":"ref24","article-title":"Dreamedit: Subject-driven image editing","author":"Li","year":"2023","journal-title":"Trans. Mach. Learn. Res."},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73390-1_7"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3680718"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00985"},{"key":"ref28","first-page":"5775","article-title":"Dpm-solver: A fast ODE solver for diffusion probabilistic model sampling in around 10 steps","author":"Lu","year":"2022","journal-title":"NeurIPS"},{"key":"ref29","article-title":"Dreamcom: Finetuning text-guided inpainting model for image composition","volume":"abs\/2309.15508","author":"Lu","year":"2023","journal-title":"CoRR"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00218"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01117"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00585"},{"key":"ref33","article-title":"Making images real again: A comprehensive survey on deep image composition","volume":"abs\/2106.14490","author":"Niu","year":"2021","journal-title":"CoRR"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1145\/882262.882269"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681079"},{"key":"ref36","article-title":"SDXL: improving latent diffusion models for high-resolution image synthesis","volume-title":"ICLR","author":"Podell","year":"2024"},{"key":"ref37","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","author":"Radford","year":"2021","journal-title":"ICML"},{"key":"ref38","article-title":"Hierarchical text-conditional image generation with CLIP latents","volume":"abs\/2204.06125","author":"Ramesh","year":"2022","journal-title":"CoRR"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02155"},{"key":"ref41","article-title":"Magic insert: Style-aware drag-and-drop","volume":"abs\/2407.02489","author":"Ruiz","year":"2024","journal-title":"CoRR"},{"key":"ref42","first-page":"36479","article-title":"Photorealistic text-to-image diffusion models with deep language understanding","author":"Saharia","year":"2022","journal-title":"NeurIPS"},{"issue":"3","key":"ref43","first-page":"595","article-title":"Elgammal. Large-scale classification of fine-art paintings: Learning the right metric on the right feature","volume":"25","author":"Saleh","year":"2015","journal-title":"Journal of Computer Science Technology"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73232-4_24"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2015.2465960"},{"key":"ref46","first-page":"2256","article-title":"Deep unsupervised learning using nonequilibrium thermodynamics","author":"Sohl-Dickstein","year":"2015","journal-title":"ICML"},{"key":"ref47","article-title":"Measuring style similarity in diffusion models","volume":"abs\/2404.01292","author":"Somepalli","year":"2024","journal-title":"CoRR"},{"key":"ref48","first-page":"11895","article-title":"Generative modeling by estimating gradients of the data distribution","author":"Song","year":"2019","journal-title":"NeurIPS"},{"key":"ref49","article-title":"Score-based generative modeling through stochastic differential equations","author":"Song","year":"2021","journal-title":"ICLR"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01756"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00769"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73033-7_27"},{"key":"ref53","article-title":"Instantstyle: Free lunch towards style-preserving in text-to-image generation","volume":"abs\/2404.02733","author":"Wang","year":"2024","journal-title":"CoRR"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00490"},{"key":"ref55","article-title":"Instantstyle-plus: Style transfer with content-preserving in text-to-image generation","volume":"abs\/2407.00788","author":"Wang","year":"2024","journal-title":"CoRR"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0977-3"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3680848"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01461"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-024-02227-z"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02148"},{"key":"ref61","article-title":"CSGO: content-style composition in text-to-image generation","volume":"abs\/2408.16766","author":"Xing","year":"2024","journal-title":"CoRR"},{"key":"ref62","article-title":"Freetuner: Any subject in any style with training-free diffusion","volume":"abs\/2405.14201","author":"Xu","year":"2024","journal-title":"CoRR"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01763"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00754"},{"key":"ref65","article-title":"Ipadapter: Text compatible image prompt adapter for text-toimage diffusion models","volume":"abs\/2308.06721","author":"Ye","year":"2023","journal-title":"CoRR"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/ACPR.2017.61"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00068"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00881"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.2969081"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1016\/j.displa.2023.102588"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.244"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73636-0_12"}],"event":{"name":"2025 IEEE\/CVF International Conference on Computer Vision (ICCV)","location":"Honolulu, HI, USA","start":{"date-parts":[[2025,10,19]]},"end":{"date-parts":[[2025,10,25]]}},"container-title":["2025 IEEE\/CVF International Conference on Computer Vision (ICCV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11443115\/11443287\/11445614.pdf?arnumber=11445614","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T06:34:36Z","timestamp":1777530876000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11445614\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":73,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01564","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}