{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T10:00:26Z","timestamp":1777888826633,"version":"3.51.4"},"reference-count":72,"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\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2023YFA1008500"],"award-info":[{"award-number":["2023YFA1008500"]}],"id":[{"id":"10.13039\/501100012166","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\/iccv51701.2025.01684","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"18121-18131","source":"Crossref","is-referenced-by-count":2,"title":["FramePainter: Endowing Interactive Image Editing with Video Diffusion Priors"],"prefix":"10.1109","author":[{"given":"Yabo","family":"Zhang","sequence":"first","affiliation":[{"name":"Harbin Institute of Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xinpeng","family":"Zhou","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yihan","family":"Zeng","sequence":"additional","affiliation":[{"name":"Huawei Noah's Ark Lab"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hang","family":"Xu","sequence":"additional","affiliation":[{"name":"Huawei Noah's Ark Lab"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hui","family":"Li","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wangmeng","family":"Zuo","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/3750722"},{"key":"ref2","author":"Balaji","year":"2022","journal-title":"ediffi: Text-to-image diffusion models with an ensemble of expert denoisers"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/3680528.3687614"},{"key":"ref4","author":"Blattmann","year":"2023","journal-title":"Stable video diffusion: Scaling latent video diffusion models to large datasets"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01764"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01764"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02062"},{"key":"ref8","author":"Chen","year":"2023","journal-title":"Videocrafter1: Open diffusion models for high-quality video generation"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00630"},{"key":"ref10","author":"Cong","year":"2023","journal-title":"Flatten: optical flowguided attention for consistent text-to-video editing"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73636-0_20"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02096"},{"key":"ref13","author":"Geyer","year":"2023","journal-title":"Tokenflow: Consistent diffusion features for consistent video editing"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72946-1_19"},{"key":"ref15","author":"He","year":"2024","journal-title":"Cameractrl: Enabling camera control for text-to-video generation"},{"key":"ref16","author":"He","year":"2022","journal-title":"Latent video diffusion models for high-fidelity video generation with arbitrary lengths"},{"key":"ref17","article-title":"Prompt-to-prompt image editing with cross attention control","author":"Hertz","year":"2023","journal-title":"ICLR"},{"key":"ref18","first-page":"8153","article-title":"Animate anyone: Consistent and controllable image-to-video synthesis for character animation","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Hu","year":"2024"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.00513"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00639"},{"key":"ref21","author":"Karaev","year":"2024","journal-title":"Cotracker3: Simpler and better point tracking by pseudolabelling real videos"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00582"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01462"},{"key":"ref24","author":"Kynk\u00e4\u00e4nniemi","year":"2022","journal-title":"The role of imagenet classes in fr \u2019echet inception distance"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00644"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73195-2_1"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00785"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00984"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00885"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i5.28206"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i6.32643"},{"key":"ref32","article-title":"Sdedit: Guided image synthesis and editing with stochastic differential equations","author":"Meng","year":"2022","journal-title":"ICLR"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00585"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00585"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00585"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.00811"},{"key":"ref37","author":"Mou","year":"2023","journal-title":"Dragondiffusion: Enabling drag-style manipulation on diffusion models"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i5.28226"},{"key":"ref39","author":"Quinn Nichol","year":"2022","journal-title":"Glide: Towards photorealistic image generation and editing with text-guided diffusion models"},{"key":"ref40","author":"Nie","year":"2023","journal-title":"The blessing of randomness: Sde beats ode in general diffusion-based image editing"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1145\/3588432.3591500"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i6.32685"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1145\/3588432.3591513"},{"key":"ref44","author":"Peng","year":"2024","journal-title":"Controlnext: Powerful and efficient control for image and video generation"},{"key":"ref45","author":"Podell","year":"2023","journal-title":"Sdxl: Improving latent diffusion models for high-resolution image synthesis"},{"key":"ref46","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford","year":"2021"},{"key":"ref47","author":"Ramesh","year":"2022","journal-title":"Hierarchical text-conditional image generation with clip latents"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.00736"},{"key":"ref50","article-title":"Photorealistic text-to-image diffusion models with deep language understanding","author":"Saharia","year":"2022","journal-title":"NeurIPS"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00844"},{"key":"ref52","author":"Shi","year":"2024","journal-title":"Lightningdrag: Lightning fast and accurate drag-based image editing emerging from videos"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0068"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00753"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00191"},{"key":"ref56","author":"Wang","year":"2023","journal-title":"Modelscope text-to-video technical report"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72667-5_3"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01461"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72983-6_15"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.00625"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00701"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72952-2_23"},{"key":"ref63","author":"Ye","year":"2023","journal-title":"Ipadapter: Text compatible image prompt adapter for text-toimage diffusion models"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.00845"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00198"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"ref68","author":"Zhang","year":"2023","journal-title":"I2vgen-xl: High-quality image-to-video synthesis via cascaded diffusion models"},{"key":"ref69","author":"Zhang","year":"2023","journal-title":"Controlvideo: Training-free controllable text-to-video generation"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i10.33114"},{"key":"ref71","article-title":"Uni-controlnet: All-in-one control to text-to-image diffusion models","author":"Zhao","year":"2024","journal-title":"NeurIPS"},{"key":"ref72","author":"Zhou","year":"2022","journal-title":"Magicvideo: Efficient video generation with latent diffusion models"}],"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\/11446297.pdf?arnumber=11446297","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T04:59:07Z","timestamp":1777611547000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11446297\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":72,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01684","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}