{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T03:29:29Z","timestamp":1777865369420,"version":"3.51.4"},"reference-count":37,"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\/501100004826","name":"Beijing Natural Science Foundation","doi-asserted-by":"publisher","award":["Z231100005923033"],"award-info":[{"award-number":["Z231100005923033"]}],"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\/iccv51701.2025.01465","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"15792-15801","source":"Crossref","is-referenced-by-count":0,"title":["Multi-Turn Consistent Image Editing"],"prefix":"10.1109","author":[{"given":"Zijun","family":"Zhou","sequence":"first","affiliation":[{"name":"Institute of Computing Technology, Chinese Academy of Sciences"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yingying","family":"Deng","sequence":"additional","affiliation":[{"name":"University of Science and Technology Beijing"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiangyu","family":"He","sequence":"additional","affiliation":[{"name":"Institute of Automation, Chinese Academy of Sciences,MAIS"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Weiming","family":"Dong","sequence":"additional","affiliation":[{"name":"Institute of Automation, Chinese Academy of Sciences,MAIS"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fan","family":"Tang","sequence":"additional","affiliation":[{"name":"Institute of Computing Technology, Chinese Academy of Sciences"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","first-page":"2","author":"Albergo","year":"2023","journal-title":"Building Normalizing Flows with Stochastic Interpolants"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.00738"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02062"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/3592116"},{"key":"ref5","first-page":"2","article-title":"Diffedit: Diffusion-based semantic image editing with mask guidance","author":"Couairon","year":"2022","journal-title":"arXiv preprint"},{"key":"ref6","first-page":"5","article-title":"Fluxspace: Disentangled semantic editing in rectified flow transformers","author":"Dalva","year":"2024","journal-title":"arXiv preprint"},{"key":"ref7","first-page":"2","article-title":"Z*: Zero-shot style transfer via attention rearrangement","author":"Deng","year":"2023","journal-title":"arXiv preprint"},{"key":"ref8","author":"Deng","year":"2024","journal-title":"FireFlow: Fast Inversion of Rectified Flow for Image Semantic Editing"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0714"},{"key":"ref10","first-page":"2","author":"Esser","year":"2024","journal-title":"Scaling Rectified Flow Transformers for High-Resolution Image Synthesis"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73411-3_23"},{"key":"ref12","article-title":"Prompt-to-prompt image editing with cross attention control","author":"Hertz","year":"2022","journal-title":"arXiv preprint"},{"key":"ref13","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume":"33","author":"Ho","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref14","first-page":"2","article-title":"Region-aware diffusion for zero-shot text-driven image editing","author":"Huang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2023.3342645"},{"key":"ref16","article-title":"Direct inversion: Boosting diffusion-based editing with 3 lines of code","author":"Ju","year":"2023","journal-title":"arXiv preprint"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00246"},{"key":"ref18","article-title":"Flowedit: Inversion-free text-based editing using pre-trained flow models","author":"Kulikov","year":"2024","journal-title":"arXiv preprint"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00192"},{"key":"ref20","first-page":"2","year":"2024","journal-title":"Flux. 1 [dev] is an open-weight, guidancedistilled model for non-commercial applications"},{"key":"ref21","first-page":"2","author":"Lipman","year":"2023","journal-title":"Flow Matching for Generative Modeling"},{"key":"ref22","author":"Liu","year":"2022","journal-title":"Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flow"},{"key":"ref23","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":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00585"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00774"},{"key":"ref26","first-page":"8162","article-title":"Improved denoising diffusion probabilistic models","volume-title":"International conference on machine learning","author":"Nichol"},{"key":"ref27","first-page":"6","volume-title":"GPT-4 Turbo","year":"2023"},{"key":"ref28","first-page":"5","article-title":"Sdxl: Improving latent diffusion models for high-resolution image synthesis","author":"Podell","year":"2023","journal-title":"arXiv preprint"},{"key":"ref29","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref31","author":"Rout","year":"2024","journal-title":"Semantic Image Inversion and Editing using Rectified Stochastic Differential Equations"},{"key":"ref32","first-page":"2","article-title":"Denoising diffusion implicit models","author":"Song","year":"2020","journal-title":"arXiv preprint"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00191"},{"key":"ref34","author":"Wang","year":"2024","journal-title":"Taming Rectified Flow for Inversion and Editing"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00706"},{"key":"ref36","first-page":"5","article-title":"Headrouter: A training-free image editing framework for mmdits by adaptively routing attention heads","author":"Xu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00068"}],"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\/11444437.pdf?arnumber=11444437","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T06:21:25Z","timestamp":1777530085000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11444437\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":37,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01465","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}