{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T06:22:31Z","timestamp":1778048551958,"version":"3.51.4"},"reference-count":52,"publisher":"IEEE","license":[{"start":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T00:00:00Z","timestamp":1772755200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T00:00:00Z","timestamp":1772755200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,3,6]]},"DOI":"10.1109\/wacv61042.2026.00404","type":"proceedings-article","created":{"date-parts":[[2026,5,5]],"date-time":"2026-05-05T19:59:32Z","timestamp":1778011172000},"page":"4150-4159","source":"Crossref","is-referenced-by-count":0,"title":["Rethinking Real Image Editing: Unleashing Diverse Editing Operators via Multi-Objective Optimization"],"prefix":"10.1109","author":[{"given":"Siyuan","family":"Wang","sequence":"first","affiliation":[{"name":"Xi’an Jiaotong-Liverpool University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xi","family":"Yang","sequence":"additional","affiliation":[{"name":"Xi’an Jiaotong-Liverpool University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zihao","family":"Zhou","sequence":"additional","affiliation":[{"name":"Xi’an Jiaotong-Liverpool University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Huiru","family":"Shao","sequence":"additional","affiliation":[{"name":"Xi’an Jiaotong-Liverpool University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rui","family":"Zhang","sequence":"additional","affiliation":[{"name":"Xi’an Jiaotong-Liverpool University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qiufeng","family":"Wang","sequence":"additional","affiliation":[{"name":"Xi’an Jiaotong-Liverpool University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Guangliang","family":"Cheng","sequence":"additional","affiliation":[{"name":"University of Liverpool"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kaizhu","family":"Huang","sequence":"additional","affiliation":[{"name":"Duke Kunshan University"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00738"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00846"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01764"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02062"},{"key":"ref5","article-title":"Gradnorm: Gradient normalization for adaptive loss balancing in deep multitask networks","author":"Chen","year":"2018","journal-title":"ICML"},{"key":"ref6","article-title":"Diffedit: Diffusion-based semantic image editing with mask guidance","author":"Couairon","year":"2023","journal-title":"ICLR"},{"key":"ref7","article-title":"Multi-task learning with deep neural networks: A survey","author":"Crawshaw","year":"2020"},{"key":"ref8","article-title":"Exploring GPT-4 vision for text-to-image synthesis evaluation","author":"Cui","year":"2024","journal-title":"ICLR"},{"key":"ref9","article-title":"Diffusion models beat gans on image synthesis","author":"Dhariwal","year":"2021","journal-title":"NeurIPS"},{"key":"ref10","article-title":"Diffusion self-guidance for control-lable image generation","author":"Epstein","year":"2023","journal-title":"NeurIPS"},{"key":"ref11","article-title":"Scaling rectified flow transformers for high-resolution image synthesis","author":"Esser","year":"2024","journal-title":"ICML"},{"key":"ref12","article-title":"Guiding instruction-based image editing via multimodal large language models","author":"Fu","year":"2024","journal-title":"ICLR"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01270-0_17"},{"key":"ref14","article-title":"Prompt-to-prompt image editing with cross-attention control","author":"Hertz","year":"2023","journal-title":"ICLR"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.595"},{"key":"ref16","article-title":"Classifier-free diffusion guidance","author":"Ho","year":"2021","journal-title":"NeurIPS"},{"key":"ref17","article-title":"Denoising diffusion probabilistic models","author":"Ho","year":"2020","journal-title":"NeurIPS"},{"key":"ref18","article-title":"ELLA: equip diffusion models with LLM for enhanced semantic alignment","author":"Hu","year":"2024","journal-title":"CoRR"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01185"},{"key":"ref20","article-title":"Artist: Aesthetically controllable text-driven stylization without training","author":"Jiang","year":"2024","journal-title":"CoRR"},{"key":"ref21","article-title":"Pnp inversion: Boosting diffusion-based editing with 3 lines of code","author":"Ju","year":"2024","journal-title":"ICLR"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00582"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00781"},{"key":"ref24","article-title":"Flux","year":"2024"},{"key":"ref25","article-title":"Flux. 1 kontext: Flow matching for in-context image generation and editing in latent space","author":"Labs","year":"2025"},{"key":"ref26","article-title":"Blip: Bootstrapping language-image pre-training for unified vision-language understanding and generation","author":"Li","year":"2022","journal-title":"ICML"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00197"},{"key":"ref28","article-title":"Sdedit: Guided image synthesis and editing with stochastic differential equations","author":"Meng","year":"2022","journal-title":"ICLR"},{"key":"ref29","article-title":"Negative-prompt inversion: Fast image inversion for editing with text-guided diffusion models","author":"Miyake","year":"2024","journal-title":"ICLR"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00585"},{"key":"ref31","article-title":"Gpt-4o system card","year":"2024"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01372"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/3588432.3591513"},{"key":"ref34","article-title":"pops: Photo-inspired diffusion operators","author":"Richardson","year":"2024","journal-title":"CoRR"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref37","article-title":"Multi-task learning as multi-objective optimization","author":"Sener","year":"2018","journal-title":"NeurIPS"},{"key":"ref38","article-title":"Deep unsupervised learning using nonequilibrium thermodynamics","author":"Sohl-Dickstein","year":"2015","journal-title":"ICML"},{"key":"ref39","article-title":"Denoising diffusion implicit models","author":"Song","year":"2021","journal-title":"ICLR"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73209-6_14"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01048"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00191"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3054719"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02158"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01761"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2025.112041"},{"key":"ref47","article-title":"Qwen-image technical report","author":"Wu","year":"2025"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00678"},{"key":"ref49","article-title":"Imagereward: Learning and evaluating human preferences for text-to-image generation","author":"Xu","year":"2023","journal-title":"NeurIPS"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01763"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00068"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i7.28622"}],"event":{"name":"2026 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV)","location":"Tucson, AZ, USA","start":{"date-parts":[[2026,3,6]]},"end":{"date-parts":[[2026,3,10]]}},"container-title":["2026 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11491838\/11491925\/11492726.pdf?arnumber=11492726","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T06:06:47Z","timestamp":1778047607000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11492726\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,6]]},"references-count":52,"URL":"https:\/\/doi.org\/10.1109\/wacv61042.2026.00404","relation":{},"subject":[],"published":{"date-parts":[[2026,3,6]]}}}