{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,7]],"date-time":"2026-04-07T16:16:38Z","timestamp":1775578598436,"version":"3.50.1"},"reference-count":38,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,7,15]],"date-time":"2024-07-15T00:00:00Z","timestamp":1721001600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,7,15]],"date-time":"2024-07-15T00:00:00Z","timestamp":1721001600000},"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":[[2024,7,15]]},"DOI":"10.1109\/icme57554.2024.10687547","type":"proceedings-article","created":{"date-parts":[[2024,9,30]],"date-time":"2024-09-30T17:24:16Z","timestamp":1727717056000},"page":"1-6","source":"Crossref","is-referenced-by-count":5,"title":["IterInv: Iterative Inversion for Pixel-Level T2I Models"],"prefix":"10.1109","author":[{"given":"Chuanming","family":"Tang","sequence":"first","affiliation":[{"name":"University of Chinese Academy of Sciences,Institute of Optics and Electronics Computer Vision Center,Beijing,China"}]},{"given":"Kai","family":"Wang","sequence":"additional","affiliation":[{"name":"Computer Vision Center,Barcelona,Spain"}]},{"given":"Joost","family":"van de Weijer","sequence":"additional","affiliation":[{"name":"Universitat Autonoma de Barcelona,Computer Vision Center,Barcelona,Spain"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Midjourney","year":"2022"},{"key":"ref2","first-page":"8821","article-title":"Zero-shot text-to-image generation","volume-title":"International Conference on Machine Learning","author":"Ramesh"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref4","article-title":"Photoreal-istic text-to-image diffusion models with deep language understanding","author":"Saharia","year":"2022"},{"key":"ref5","article-title":"Deepfloyd-if","author":"Shonenkov","year":"2023"},{"key":"ref6","article-title":"Glide: Towards photorealistic image generation and editing with text-guided diffusion models","author":"Nichol","year":"2021"},{"key":"ref7","article-title":"Hierarchical text-conditional image generation with clip latents","author":"Ramesh","year":"2022"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02062"},{"key":"ref9","article-title":"Diffedit: Diffusion-based semantic image editing with mask guidance","volume-title":"The Eleventh International Conference on Learning Representations","author":"Couairon"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00221"},{"key":"ref11","article-title":"Prompt-to-prompt image editing with cross attention control","volume-title":"International Conference on Learning Representations","author":"Hertz"},{"key":"ref12","article-title":"Stylediffusion: Prompt-embedding inversion for text-based editing","author":"Li","year":"2023"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00191"},{"key":"ref14","article-title":"Mdp: A generalized framework for text-guided image editing by manipulating the diffusion path","author":"Wang","year":"2023"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19784-0_41"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01410"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00246"},{"key":"ref18","article-title":"Diffusion-based image translation using disentangled style and content representation","volume-title":"The Eleventh International Conference on Learning Representations","author":"Kwon"},{"key":"ref19","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford"},{"key":"ref20","article-title":"Muse: Text-to-image generation via masked generative transformers","author":"Chang","year":"2023"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19784-0_6"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00686"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01764"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00582"},{"key":"ref25","article-title":"SDEdit: Guided image synthesis and editing with stochastic differential equations","volume-title":"International Conference on Learning Representations","author":"Meng"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/3588432.3591513"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02107"},{"key":"ref28","article-title":"Dynamic prompt learning: Addressing cross-attention leakage for text-based image editing","author":"Wang","year":"2023","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref29","article-title":"Denoising diffusion implicit models","volume-title":"International Conference on Learning Representations","author":"Song"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00585"},{"key":"ref31","article-title":"Classifier-free diffusion guidance","volume-title":"NeurIPS 2021 Workshop on Deep Generative Models and Downstream Applications","author":"Ho"},{"key":"ref32","article-title":"Negative-prompt inversion: Fast image inversion for editing with text-guided diffusion models","author":"Miyake","year":"2023"},{"key":"ref33","article-title":"Improving negative-prompt inversion via proximal guidance","author":"Han","year":"2023"},{"key":"ref34","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume":"33","author":"Ho","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref35","article-title":"Diffusers: State-of-the-art diffusion models","author":"von Platen","year":"2022"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00068"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ACSSC.2003.1292216"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.595"}],"event":{"name":"2024 IEEE International Conference on Multimedia and Expo (ICME)","location":"Niagara Falls, ON, Canada","start":{"date-parts":[[2024,7,15]]},"end":{"date-parts":[[2024,7,19]]}},"container-title":["2024 IEEE International Conference on Multimedia and Expo (ICME)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10685847\/10687354\/10687547.pdf?arnumber=10687547","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,1]],"date-time":"2024-10-01T05:56:22Z","timestamp":1727762182000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10687547\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,7,15]]},"references-count":38,"URL":"https:\/\/doi.org\/10.1109\/icme57554.2024.10687547","relation":{},"subject":[],"published":{"date-parts":[[2024,7,15]]}}}