{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T03:28:17Z","timestamp":1777865297627,"version":"3.51.4"},"reference-count":68,"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"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62302297,72192821,62272447,62472282,62472285"],"award-info":[{"award-number":["62302297,72192821,62272447,62472282,62472285"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["YG2023QNB17,YG2024QNA44"],"award-info":[{"award-number":["YG2023QNB17,YG2024QNA44"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004826","name":"Beijing Natural Science Foundation","doi-asserted-by":"publisher","award":["L222117"],"award-info":[{"award-number":["L222117"]}],"id":[{"id":"10.13039\/501100004826","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.01416","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"15266-15276","source":"Crossref","is-referenced-by-count":0,"title":["Pinco: Position-Induced Consistent Adapter for Diffusion Transformer in Foreground-Conditioned Inpainting"],"prefix":"10.1109","author":[{"given":"Guangben","family":"Lu","sequence":"first","affiliation":[{"name":"Shanghai Jiao Tong University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuzhen","family":"Du","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yizhe","family":"Tang","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhimin","family":"Sun","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ran","family":"Yi","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yifan","family":"Qi","sequence":"additional","affiliation":[{"name":"Tencent"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tianyi","family":"Wang","sequence":"additional","affiliation":[{"name":"Tencent"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lizhuang","family":"Ma","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fangyuan","family":"Zou","sequence":"additional","affiliation":[{"name":"Tencent"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","year":"2023","journal-title":"Adobe firefly, 2023"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01767"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/3592450"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.2307\/j.ctt17t74vv.65"},{"key":"ref5","author":"Bhat","year":"2023","journal-title":"Zoedepth: Zero-shot transfer by combining relative and metric depth"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/3592116"},{"key":"ref7","author":"Chen","year":"2024","journal-title":"Virtualmodel: Generating object-id-retentive human-object interaction image by diffusion model for e-commerce marketing"},{"key":"ref8","author":"Chen","year":"2023","journal-title":"Disenbooth: Identitypreserving disentangled tuning for subject-driven text-toimage generation"},{"key":"ref9","author":"Chen","year":"2023","journal-title":"Pixart-alpha: Fast training of diffusion transformer for photorealistic text-to-image synthesis"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00630"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3118287"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00428"},{"key":"ref13","author":"Creative","year":"2023","journal-title":"Flux.1-dev controlnet inpainting beta, 2024"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3680853"},{"key":"ref15","author":"Du","year":"2024","journal-title":"Exploring real&synthetic dataset and linear attention in image restoration"},{"key":"ref16","author":"Elarabawy","year":"2022","journal-title":"Direct inversion: Optimization-free text-driven real image editing with diffusion models"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW63382.2024.00744"},{"key":"ref18","article-title":"Scaling rectified flow transformers for high-resolution image synthesis","volume-title":"Forty-first International Conference on Machine Learning","author":"Esser"},{"key":"ref19","volume-title":"Scaling rectified flow transformers for high-resolution image synthesis","author":"Esser","year":"2024"},{"key":"ref20","author":"Gal","year":"2022","journal-title":"An image is worth one word: Personalizing text-toimage generation using textual inversion"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2025.3636582"},{"key":"ref22","author":"Hertz","year":"2022","journal-title":"Prompt-to-prompt image editing with cross attention control"},{"key":"ref23","article-title":"Gans trained by a two time-scale update rule converge to a local nash equilibrium","volume":"30","author":"Heusel","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2025.3541625"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72661-3_9"},{"key":"ref26","volume-title":"Black Forest Labs. Flux-fill","year":"2024"},{"key":"ref27","volume-title":"Black Forest Labs. Flux","year":"2024"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/3610543.3626172"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.624"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02083"},{"key":"ref31","author":"Li","year":"2024","journal-title":"Hunyuan-dit: A powerful multi-resolution diffusion transformer with fine-grained chinese understanding"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72673-6_20"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00747"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2025\/177"},{"key":"ref36","author":"Liu","year":"2023","journal-title":"Cones: Concept neurons in diffusion models for customized generation"},{"key":"ref37","first-page":"57500","article-title":"Cones 2: Customizable image synthesis with multiple subjects","volume-title":"Proceedings of the 37th International Conference on Neural Information Processing Systems","author":"Liu"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01117"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/s41095-023-0371-3"},{"key":"ref40","author":"Manukyan","year":"2023","journal-title":"Hd-painter: high-resolution and prompt-faithful text-guided image inpainting with diffusion models"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00585"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i5.28226"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"ref45","volume-title":"Sdxl: Improving latent diffusion models for high-resolution image synthesis","author":"Podell","year":"2023"},{"key":"ref46","author":"Ravi","year":"2024","journal-title":"Sam 2: Segment anything in images and videos"},{"key":"ref47","volume-title":"High-resolution image synthesis with latent diffusion models","author":"Rombach","year":"2021"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02155"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2023.127063"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01909"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-024-02184-7"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.01709"},{"key":"ref54","author":"Team","year":"2024","journal-title":"Kolors: Effective training of diffusion model for photorealistic text-to-image synthesis"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1007\/s41095-022-0331-3"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00191"},{"key":"ref57","author":"Wang","year":"2024","journal-title":"Instantid: Zero-shot identity-preserving generation in seconds"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i12.26701"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00461"},{"key":"ref60","author":"Yang","year":"2023","journal-title":"Magicremover: Tuning-free text-guided image inpainting with diffusion models"},{"key":"ref61","author":"Ye","year":"2023","journal-title":"Ipadapter: Text compatible image prompt adapter for text-toimage diffusion models"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3432529"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"ref65","author":"Zhang","year":"2023","journal-title":"Llama-adapter: Efficient fine-tuning of language models with zero-init attention"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.26599\/AIR.2024.9150038"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72646-0_7"},{"key":"ref68","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\/11444567.pdf?arnumber=11444567","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T06:12:21Z","timestamp":1777529541000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11444567\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":68,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01416","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}