{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T03:28:13Z","timestamp":1777865293402,"version":"3.51.4"},"reference-count":62,"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\/iccv51701.2025.01785","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"19206-19215","source":"Crossref","is-referenced-by-count":0,"title":["SuperEdit: Rectifying and Facilitating Supervision for Instruction-Based Image Editing"],"prefix":"10.1109","author":[{"given":"Ming","family":"Li","sequence":"first","affiliation":[{"name":"ByteDance Intelligent Creation"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xin","family":"Gu","sequence":"additional","affiliation":[{"name":"ByteDance Intelligent Creation"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fan","family":"Chen","sequence":"additional","affiliation":[{"name":"ByteDance Intelligent Creation"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaoying","family":"Xing","sequence":"additional","affiliation":[{"name":"ByteDance Intelligent Creation"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Longyin","family":"Wen","sequence":"additional","affiliation":[{"name":"ByteDance Intelligent Creation"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chen","family":"Chen","sequence":"additional","affiliation":[{"name":"Center for Research in Computer Vision, University of Central Florida"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sijie","family":"Zhu","sequence":"additional","affiliation":[{"name":"ByteDance Intelligent Creation"}],"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","article-title":"ediff-i: Text-to-image diffusion models with an ensemble of expert denoisers","author":"Balaji","year":"2022","journal-title":"arXiv preprint"},{"key":"ref3","article-title":"Improving image generation with better captions","volume-title":"Computer Science","author":"Betker","year":"2023"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01764"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02062"},{"key":"ref6","article-title":"Diffedit: Diffusion-based semantic image editing with mask guidance","author":"Couairon","year":"2023","journal-title":"ICLR"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02285"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00709"},{"key":"ref9","article-title":"Diffusion models beat gans on image synthesis","volume-title":"NeurIPS","author":"Dhariwal","year":"2021"},{"key":"ref10","article-title":"Scaling rectified flow transformers for high-resolution image synthesis","volume-title":"ICML","author":"Esser","year":"2024"},{"key":"ref11","article-title":"Reinforcement learning for fine-tuning text-to-image diffusion models","author":"Fan","year":"2024","journal-title":"NeurIPS"},{"key":"ref12","article-title":"Guiding instruction-based image editing via multimodal large language models","author":"Fu","year":"2024","journal-title":"ICLR"},{"key":"ref13","article-title":"Seed-data-edit technical report: A hybrid dataset for instructional image editing","author":"Ge","year":"2024","journal-title":"arXiv preprint"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01208"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2270"},{"key":"ref16","article-title":"Multi-reward as condition for instruction-based image editing","author":"Gu","year":"2025","journal-title":"ICLR"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00667"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00667"},{"key":"ref19","article-title":"Prompt-to-prompt image editing with cross-attention control","author":"Hertz","year":"2023","journal-title":"ICLR"},{"key":"ref20","article-title":"Classifier-free diffusion guidance","author":"Ho","year":"2022","journal-title":"arXiv preprint"},{"key":"ref21","article-title":"Denoising diffusion probabilistic models","author":"Ho","year":"2020","journal-title":"NeurIPS"},{"key":"ref22","article-title":"Ella: Equip diffusion models with 11 m for enhanced semantic alignment","author":"Hu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.52202\/075280-3443"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00799"},{"key":"ref25","article-title":"Hq-edit: A high-quality dataset for instruction-based image editing","author":"Hui","year":"2024","journal-title":"arXiv preprint"},{"key":"ref26","article-title":"Rlaif: Scaling reinforcement learning from human feedback with ai feedback","author":"Lee","year":"2023","journal-title":"arXiv preprint"},{"key":"ref27","article-title":"Controlnet++: Improving conditional controls with efficient consistency feedback","author":"Li","year":"2024","journal-title":"ECCV"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00674"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00747"},{"key":"ref30","article-title":"Visual instruction tuning","author":"Liu","year":"2024","journal-title":"NeurIPS"},{"key":"ref31","article-title":"Sdedit: Guided image synthesis and editing with stochastic differential equations","volume-title":"ICLR","author":"Meng","year":"2022"},{"key":"ref32","article-title":"Training language models to follow instructions with human feedback","author":"Ouyang","year":"2022","journal-title":"NeurIPS"},{"key":"ref33","article-title":"Kosmos-g: Generating images in context with multimodal large language models","author":"Pan","year":"2024","journal-title":"ICLR"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1145\/3588432.3591513"},{"key":"ref35","article-title":"Pytorch: An imperative style, high-performance deep learning library","author":"Paszke","year":"2019","journal-title":"NeurIPS"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02107"},{"key":"ref37","article-title":"Sdxl: Improving latent diffusion models for high-resolution image synthesis","volume-title":"ICLR","author":"Podell","year":"2023"},{"key":"ref38","article-title":"Learning transferable visual models from natural language supervision","author":"Radford","year":"2021","journal-title":"ICML"},{"key":"ref39","volume-title":"Direct preference optimization: Your language model is secretly a reward model. NeurIPS","author":"Rafailov","year":"2024"},{"key":"ref40","article-title":"Zero-shot text-to-image generation","author":"Ramesh","year":"2021","journal-title":"ICML"},{"key":"ref41","article-title":"Hierarchical text-conditional image generation with clip latents","author":"Ramesh","year":"2022","journal-title":"arXiv preprint"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref44","article-title":"Photorealistic text-to-image diffusion models with deep language understanding","author":"Saharia","year":"2022","journal-title":"NeurIPS"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00847"},{"key":"ref46","article-title":"Lime: localized image editing via attention regularization in diffusion models","author":"Simsar","year":"2023","journal-title":"arXiv preprint"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00621"},{"key":"ref48","article-title":"Deep unsupervised learning using nonequilibrium thermodynamics","author":"Sohl-Dickstein","year":"2015","journal-title":"ICML"},{"key":"ref49","article-title":"Denoising diffusion implicit models","author":"Song","year":"2021","journal-title":"ICLR"},{"key":"ref50","article-title":"Kolors: Effective training of diffusion model for photorealistic text-to-image synthesis","volume-title":"arXiv preprint","author":"Team","year":"2024"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00191"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00786"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02148"},{"key":"ref54","article-title":"Imagereward: Learning and evaluating human preferences for text-to-image generation","author":"Xu","year":"2023","journal-title":"NeurIPS"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00854"},{"key":"ref56","article-title":"Towards understanding the working mechanism of text-to-image diffusion model","author":"Yi","year":"2024","journal-title":"arXiv preprint"},{"key":"ref57","article-title":"Inpaint anything: Segment anything meets image inpainting","author":"Yu","year":"2023","journal-title":"arXiv preprint"},{"key":"ref58","article-title":"Magicbrush: A manually annotated dataset for instruction-guided image editing","author":"Zhang","year":"2024","journal-title":"NeurIPS"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00862"},{"key":"ref61","article-title":"Cross-attention makes inference cumbersome in text-to-image diffusion models","author":"Zhang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref62","article-title":"Ultraedit: Instruction-based fine-grained image editing at scale","author":"Zhao","year":"2024","journal-title":"arXiv preprint"}],"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\/11443607.pdf?arnumber=11443607","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T06:10:50Z","timestamp":1777529450000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11443607\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":62,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01785","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}