{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T10:21:40Z","timestamp":1777890100635,"version":"3.51.4"},"reference-count":67,"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 R&D Program of China","doi-asserted-by":"publisher","award":["2022ZD0161501"],"award-info":[{"award-number":["2022ZD0161501"]}],"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\/iccv51701.2025.01417","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"15277-15287","source":"Crossref","is-referenced-by-count":0,"title":["Edicho: Consistent Image Editing in the Wild"],"prefix":"10.1109","author":[{"given":"Qingyan","family":"Bai","sequence":"first","affiliation":[{"name":"HKUST"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hao","family":"Ouyang","sequence":"additional","affiliation":[{"name":"Ant Group"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yinghao","family":"Xu","sequence":"additional","affiliation":[{"name":"Stanford University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qiuyu","family":"Wang","sequence":"additional","affiliation":[{"name":"Ant Group"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ceyuan","family":"Yang","sequence":"additional","affiliation":[{"name":"CUHK"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ka Leong","family":"Cheng","sequence":"additional","affiliation":[{"name":"HKUST"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yujun","family":"Shen","sequence":"additional","affiliation":[{"name":"Ant Group"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qifeng","family":"Chen","sequence":"additional","affiliation":[{"name":"HKUST"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/3641519.3657423"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3592450"},{"key":"ref3","article-title":"Stable video diffusion: Scaling latent video diffusion models to large datasets","author":"Blattmann","year":"2023","journal-title":"arXiv preprint"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02161"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01764"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02062"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"ref8","first-page":"2","article-title":"Videocrafter1: Open diffusion models for high-quality video generation","author":"Chen","year":"2023","journal-title":"arXiv preprint"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.52202\/079017-2669"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00630"},{"key":"ref11","article-title":"Diffusion models beat GANs on image synthesis","volume-title":"Adv. Neural Inform. Process. Syst.","author":"Dhariwal","year":"2021"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00923"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00675"},{"key":"ref14","article-title":"Lumina-t2x: Scalable flow-based large diffusion transformer for flexible resolution generation","volume-title":"Int. Conf. Learn. Represent.","author":"Gao","year":"2025"},{"key":"ref15","first-page":"2","article-title":"Multi-reward as condition for instruction-based image editing","author":"Gu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00424"},{"key":"ref17","first-page":"2","article-title":"Prompt-to-prompt image editing with cross attention control","volume-title":"Int. Conf. Learn. Represent.","author":"Hertz","year":"2023"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00457"},{"key":"ref19","first-page":"2","article-title":"Denoising diffusion probabilistic models","volume-title":"Adv. Neural Inform. Process. Syst.","author":"Ho","year":"2020"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0628"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00727"},{"key":"ref22","first-page":"8","article-title":"LoRA: Low-rank adaptation of large language models","volume-title":"Int. Conf. Learn. Represent.","author":"Hu","year":"2022"},{"key":"ref23","first-page":"2","article-title":"Composer: Creative and controllable image synthesis with composable conditions","author":"Huang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00615"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72661-3_9"},{"key":"ref26","first-page":"2","article-title":"Pnp inversion: Boosting diffusion-based editing with 3 lines of code","volume-title":"Int. Conf. Learn. Represent.","author":"Ju","year":"2024"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73033-7_2"},{"key":"ref28","first-page":"2","article-title":"Elucidating the design space of diffusion-based generative models","volume-title":"Adv. Neural Inform. Process. Syst.","author":"Karras","year":"2022"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00582"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01462"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00246"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00192"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73220-1_5"},{"key":"ref34","first-page":"2","article-title":"Ctrladapter: An efficient and versatile framework for adapting diverse controls to any diffusion model","volume-title":"Int. Conf. Learn. Represent.","author":"Lin","year":"2025"},{"key":"ref35","first-page":"2","article-title":"SDEdit: Guided image synthesis and editing with stochastic differential equations","volume-title":"Int. Conf. Learn. Represent.","author":"Meng","year":"2022"},{"key":"ref36","first-page":"2","article-title":"Negative-prompt inversion: Fast image inversion for editing with text-guided diffusion models","author":"Miyake","year":"2023","journal-title":"arXiv preprint"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00585"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i5.28226"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00790"},{"key":"ref40","first-page":"2","article-title":"Improved denoising diffusion probabilistic models","volume-title":"Int. Conf. Mach. Learn.","author":"Nichol","year":"2021"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.00773"},{"key":"ref42","first-page":"2","article-title":"Dreamfusion: Text-to-3d using 2d diffusion","volume-title":"Int. Conf. Learn. Represent.","author":"Poole","year":"2023"},{"key":"ref43","first-page":"6","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Int. Conf. Mach. Learn.","author":"Radford","year":"2021"},{"key":"ref44","first-page":"3","article-title":"Segment anything meets point tracking","author":"Raji\u010d","year":"2023","journal-title":"arXiv"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.291"},{"key":"ref46","volume-title":"Adobe firefly: Free generative ai for creatives","year":"2023"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.17487\/rfc1321"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref49","article-title":"Semantic image inversion and editing using rectified stochastic differential equations","volume-title":"Int. Conf. Learn. Represent.","author":"Rout","year":"2025"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02155"},{"key":"ref51","article-title":"Denoising diffusion implicit models","volume-title":"Int. Conf. Learn. Represent.","author":"Song","year":"2021"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0068"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1145\/3658157"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00191"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73232-4_25"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01956"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00443"},{"key":"ref59","first-page":"2","article-title":"Genartist: Multimodal 11 m as an agent for unified image generation and editing","author":"Wang","year":"2024","journal-title":"Adv. Neural Inform. Process. Syst."},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01929"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01763"},{"key":"ref62","first-page":"2","article-title":"Textctrl: Diffusion-based scene text editing with prior guidance control","volume-title":"Adv. Neural Inform. Process. Syst.","author":"Zeng","year":"2024"},{"key":"ref63","first-page":"3","article-title":"A tale of two features: Stable diffusion complements dino for zero-shot semantic correspondence","volume-title":"Adv. Neural Inform. Process. Syst.","author":"Zhang","year":"2024"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr42600.2020.00519"},{"key":"ref66","first-page":"2","article-title":"Uni-controlnet: All-in-one control to text-to-image diffusion models","volume-title":"Adv. Neural Inform. Process. Syst.","author":"Zhao","year":"2024"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01130"}],"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\/11444872.pdf?arnumber=11444872","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:30:32Z","timestamp":1777613432000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11444872\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":67,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01417","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}