{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T03:30:52Z","timestamp":1777865452566,"version":"3.51.4"},"reference-count":55,"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\/iccv51701.2025.01756","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"18895-18905","source":"Crossref","is-referenced-by-count":0,"title":["UIP2P: Unsupervised Instruction-Based Image Editing via Edit Reversibility Constraint"],"prefix":"10.1109","author":[{"given":"Enis","family":"Simsar","sequence":"first","affiliation":[{"name":"ETH Zϋrich - DALAB"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Alessio","family":"Tonioni","sequence":"additional","affiliation":[{"name":"Google,Switzerland"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yongqin","family":"Xian","sequence":"additional","affiliation":[{"name":"Google,Switzerland"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Thomas","family":"Hofmann","sequence":"additional","affiliation":[{"name":"ETH Zϋrich - DALAB"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Federico","family":"Tombari","sequence":"additional","affiliation":[{"name":"Technical University of Munich"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Gpt-4 technical report","author":"Achiam","year":"2023","journal-title":"arXiv preprint"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01767"},{"issue":"3","key":"ref3","article-title":"Improving image generation with better captions","volume":"2","author":"Betker","year":"2023","journal-title":"Computer Science"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.52202\/079017-3367"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01764"},{"key":"ref6","article-title":"Language models are few-shot learners","volume-title":"Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, NeurIPS 2020","author":"Brown","year":"2020"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr46437.2021.00356"},{"key":"ref8","article-title":"Diffedit: Diffusion-based semantic image editing with mask guidance","volume-title":"The Eleventh International Conference on Learning Representations","author":"Couairon","year":"2023"},{"key":"ref9","article-title":"The Rating of Chess Players, Past and Present","author":"Elo","year":"1978","journal-title":"Batsford London"},{"key":"ref10","article-title":"Guiding instruction-based image editing via multimodal large language models","author":"Fu","year":"2023","journal-title":"arXiv preprint"},{"key":"ref11","volume-title":"An image is worth one word: Personalizing text-to-image generation using textual inversion","author":"Gal","year":"2022"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/3528223.3530164"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.01208"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00667"},{"key":"ref15","article-title":"Prompt-to-prompt image editing with cross attention control","author":"Hertz","year":"2022","journal-title":"CoRR"},{"key":"ref16","article-title":"Classifier-free diffusion guidance","volume-title":"NeurIPS 2021 Workshop on Deep Generative Models and Downstream Applications","author":"Ho","year":"2021"},{"key":"ref17","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume":"33","author":"Ho","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00799"},{"key":"ref19","article-title":"HQ-edit: A high-quality dataset for instruction-based image editing","volume-title":"The Thirteenth International Conference on Learning Representations","author":"Hui","year":"2025"},{"key":"ref20","article-title":"Direct inversion: Boosting diffusion-based editing with 3 lines of code","author":"Ju","year":"2023","journal-title":"arXiv preprint"},{"key":"ref21","article-title":"Imagic: Text-based real image editing with diffusion models","author":"Kawar","year":"2022","journal-title":"CoRR"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00246"},{"key":"ref23","article-title":"Decoupled weight decay regularization","author":"Loshchilov","year":"2017","journal-title":"arXiv preprint"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01117"},{"key":"ref25","article-title":"SDEdit: Guided image synthesis and editing with stochastic differential equations","volume-title":"International Conference on Learning Representations","author":"Meng","year":"2022"},{"key":"ref26","article-title":"Null-text inversion for editing real images using guided diffusion models","author":"Mokady","year":"2022","journal-title":"CoRR"},{"key":"ref27","first-page":"16784","article-title":"GLIDE: towards photorealistic image generation and editing with text-guided diffusion models","volume-title":"International Conference on Machine Learning","author":"Nichol","year":"2022"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/3588432.3591513"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00209"},{"key":"ref30","volume-title":"Prolific","year":"2025"},{"key":"ref31","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proceedings of the 38th International Conference on Machine Learning","author":"Radford","year":"2021"},{"key":"ref32","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proceedings of the 38th International Conference on Machine Learning","author":"Radford","year":"2021"},{"key":"ref33","article-title":"Hierarchical text-conditional image generation with CLIP latents","author":"Ramesh","year":"2022","journal-title":"CoRR"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02155"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2643"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1238"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-69544-6_38"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01338"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/WACV61041.2025.00032"},{"key":"ref41","article-title":"Dual diffusion implicit bridges for image-to-image translation","author":"Su","year":"2022","journal-title":"arXiv preprint"},{"key":"ref42","article-title":"Gemini: a family of highly capable multimodal models","author":"Team","year":"2023","journal-title":"arXiv preprint"},{"key":"ref43","article-title":"Gemma 2: Improving open language models at a practical size","author":"Team","year":"2024","journal-title":"arXiv preprint"},{"key":"ref44","article-title":"Dynamic prompt learning: Addressing cross-attention leakage for text-based image editing","volume-title":"Thirty-seventh Conference on Neural Information Processing Systems","author":"Wang","year":"2023"},{"key":"ref45","volume-title":"Mdp: A generalized framework for text-guided image editing by manipulating the diffusion path","author":"Wang","year":"2023"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01461"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00678"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00189"},{"key":"ref49","article-title":"Cyclenet: Rethinking cycle consistent in text-guided diffusion for image manipulation","author":"Xu","year":"2023","journal-title":"Advances in Neural Information Processing Systems (NeurIPS)"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01763"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1365"},{"key":"ref52","article-title":"HIVE: harnessing human feedback for instructional visual editing","author":"Zhang","year":"2023","journal-title":"CoRR"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.52202\/079017-0100"},{"key":"ref54","article-title":"Chatbot arena: benchmarking $l l ~\\text{ms}$ in the wild with elo ratings","author":"Zheng","year":"2024","journal-title":"LMSYS Org"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/iccv.2017.244"}],"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\/11443410.pdf?arnumber=11443410","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T06:35:05Z","timestamp":1777530905000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11443410\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":55,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01756","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}