{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,24]],"date-time":"2026-02-24T08:41:20Z","timestamp":1771922480767,"version":"3.50.1"},"reference-count":38,"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\/iccvw69036.2025.00454","type":"proceedings-article","created":{"date-parts":[[2026,2,23]],"date-time":"2026-02-23T20:44:02Z","timestamp":1771879442000},"page":"4380-4389","source":"Crossref","is-referenced-by-count":0,"title":["A Plug-and-Play Approach for Robust Image Editing in Text-to-Image Diffusion Models"],"prefix":"10.1109","author":[{"given":"Hyunwook","family":"Jo","sequence":"first","affiliation":[{"name":"Inha University,Department of Electrical and Computer Engineering,Incheon,Korea,22212"}]},{"given":"Jiseung","family":"Maeng","sequence":"additional","affiliation":[{"name":"Inha University,Department of Electrical and Computer Engineering,Incheon,Korea,22212"}]},{"given":"Jun Hyung","family":"Park","sequence":"additional","affiliation":[{"name":"Inha University,Department of Electrical and Computer Engineering,Incheon,Korea,22212"}]},{"given":"Namhyuk","family":"Ahn","sequence":"additional","affiliation":[{"name":"Inha University,Department of Electrical and Computer Engineering,Incheon,Korea,22212"}]},{"given":"In Kyu","family":"Park","sequence":"additional","affiliation":[{"name":"Inha University,Department of Electrical and Computer Engineering,Incheon,Korea,22212"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/iccv.2019.00453"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02062"},{"key":"ref3","article-title":"DiffEdit: Diffusion-based semantic image editing with mask guidance","volume-title":"Proc. International Conference on Learning Representations","author":"Couairon"},{"key":"ref4","first-page":"2","article-title":"An image is worth one word: Personalizing text-to-image generation using textual inversion","volume-title":"Proc. International Conference on Learning Representations","author":"Gal"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.5555\/2969033.2969125"},{"key":"ref6","article-title":"Prompt-to-prompt image editing with cross-attention control","volume-title":"Proc. International Conference on Learning Representations","author":"Hertz"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58536-5_2"},{"key":"ref8","article-title":"Direct inversion: Boosting diffusion-based editing with 3 lines of code","volume-title":"Proc. International Conference on Learning Representations","author":"Ju"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00453"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr42600.2020.00813"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00582"},{"key":"ref12","first-page":"2","article-title":"Auto-encoding variational bayes","volume-title":"Proc. International Conference on Learning Representations","author":"Kingma"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00747"},{"key":"ref14","article-title":"Negative-prompt inversion: Fast image inversion for editing with text-guided diffusion models","volume":"abs\/2305.16807","author":"Miyake","year":"2023","journal-title":"CoRR"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00585"},{"key":"ref16","article-title":"Invertible conditional GANs for image editing","volume":"abs\/1611.06355","author":"Perarnau","year":"2016","journal-title":"CoRR"},{"key":"ref17","article-title":"SDXL: Improving latent diffusion models for high-resolution image synthesis","volume-title":"Proc. International Conference on Learning Representations","author":"Podell"},{"key":"ref18","first-page":"8821","article-title":"Zero-shot text-to-image generation","volume-title":"Proc. International Conference on Machine Learning","author":"Ramesh"},{"key":"ref19","article-title":"Hierarchical text-conditional image generation with CLIP latents","volume":"abs\/2204.06125","author":"Ramesh","year":"2022","journal-title":"CoRR"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02155"},{"key":"ref22","article-title":"Photorealis-tic text-to-image diffusion models with deep language understanding","volume-title":"Proc. Advances in Neural Information Processing Systems","author":"Saharia","year":"2022"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00844"},{"key":"ref24","article-title":"Improving image captioning with better use of captions","volume":"abs\/2006.11807","author":"Shi","year":"2020","journal-title":"CoRR"},{"key":"ref25","first-page":"2256","article-title":"Deep unsupervised learning using nonequilibrium thermodynamics","volume-title":"Proc. International Conference on Machine Learning","author":"Sohl-Dickstein"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01048"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00191"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/3592451"},{"key":"ref29","first-page":"4790","article-title":"Conditional image generation with pixelcnn decoders","volume-title":"Proc. Advances in Neural Information Processing Systems","author":"van den Oord","year":"2016"},{"key":"ref30","first-page":"1747","article-title":"Pixel recurrent neural networks","volume-title":"Proc. International Conference on Machine Learning","author":"van den Oord"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/tip.2003.819861"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00706"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.00605"},{"key":"ref34","article-title":"Inversion-free image editing with natural language","volume":"abs\/2312.04965","author":"Xu","year":"2023","journal-title":"CoRR"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00068"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46454-1_36"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.244"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58520-4_35"}],"event":{"name":"2025 IEEE\/CVF International Conference on Computer Vision Workshops (ICCVW)","location":"Honolulu, HI, USA","start":{"date-parts":[[2025,10,19]]},"end":{"date-parts":[[2025,10,20]]}},"container-title":["2025 IEEE\/CVF International Conference on Computer Vision Workshops (ICCVW)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11373940\/11374285\/11375800.pdf?arnumber=11375800","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,24]],"date-time":"2026-02-24T07:36:18Z","timestamp":1771918578000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11375800\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":38,"URL":"https:\/\/doi.org\/10.1109\/iccvw69036.2025.00454","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}