{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,7]],"date-time":"2026-07-07T15:56:39Z","timestamp":1783439799790,"version":"3.54.6"},"reference-count":63,"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\/iccv51701.2025.01609","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"17324-17334","source":"Crossref","is-referenced-by-count":1,"title":["Omnipaint: Mastering Object-Oriented Editing Via Disentangled Insertion-Removal Inpainting"],"prefix":"10.1109","author":[{"given":"Yongsheng","family":"Yu","sequence":"first","affiliation":[{"name":"University of Rochester"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ziyun","family":"Zeng","sequence":"additional","affiliation":[{"name":"University of Rochester"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Haitian","family":"Zheng","sequence":"additional","affiliation":[{"name":"Adobe Research"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiebo","family":"Luo","sequence":"additional","affiliation":[{"name":"University of Rochester"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-020-01336-9"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3721238.3730673"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00132"},{"key":"ref4","article-title":"Baking gaussian splatting into diffusion denoiser for fast and scalable single-stage image-to-3d generation and reconstruction","author":"Cai","year":"2024","journal-title":"arXiv"},{"key":"ref5","article-title":"Omnivcus: Feedforward subject-driven video customization with multimodal control conditions","author":"Cai","year":"2025","journal-title":"arXiv"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW63382.2024.00788"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00630"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72643-9_5"},{"key":"ref9","article-title":"CLIPAway: Harmonizing focused embeddings for removing objects via diffusion models","volume-title":"NeurIPS","author":"Ekin","year":"2024"},{"key":"ref10","article-title":"Scaling rectified flow transformers for high-resolution image synthesis","volume-title":"ICML","author":"Esser","year":"2024"},{"key":"ref11","article-title":"Dreamsim: Learning new dimensions of human visual similarity using synthetic data","volume-title":"NeurIPS","author":"Fu","year":"2023"},{"key":"ref12","article-title":"Guiding instruction-based image editing via multimodal large language models","volume-title":"ICLR","author":"Fu","year":"2024"},{"key":"ref13","article-title":"Gans trained by a two time-scale update rule converge to a local nash equilibrium","volume-title":"NeurIPS","author":"Heusel","year":"2017"},{"key":"ref14","article-title":"Lora: Low-rank adaptation of large language models","volume-title":"ICLR","author":"Hu","year":"2022"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72673-6_26"},{"key":"ref16","article-title":"Mmigbench: Towards comprehensive and explainable evaluation of multi-modal image generation models","author":"Hua","year":"2025","journal-title":"arXiv"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00889"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02277"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00510"},{"key":"ref20","article-title":"Segment anything in high quality","volume-title":"NeurIPS","author":"Ke","year":"2023"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1780"},{"key":"ref23","article-title":"Flux","year":"2024"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73390-1_13"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01309"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01049"},{"key":"ref27","article-title":"Brushedit: All-in-one image inpainting and editing","author":"Li","year":"2024","journal-title":"arXiv"},{"key":"ref28","article-title":"Flow matching for generative modeling","volume-title":"ICLR","author":"Lipman","year":"2023"},{"key":"ref29","article-title":"Tango: Co-speech gesture video reenactment with hierarchical audio motion embedding and diffusion interpolation","author":"Liu","year":"2024","journal-title":"arXiv"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.01274"},{"key":"ref31","article-title":"Flow straight and fast: Learning to generate and transfer data with rectified flow","volume-title":"ICLR","author":"Liu","year":"2023"},{"key":"ref32","article-title":"Object removal lora of flux fill dev","year":"2025"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00883"},{"key":"ref34","article-title":"GLIDE: towards photorealistic image generation and editing with text-guided diffusion models","volume-title":"ICML","author":"Nichol","year":"2022"},{"key":"ref35","article-title":"Dinov2: Learning robust visual features without supervision","author":"Oquab","year":"2024","journal-title":"TMLR"},{"key":"ref36","article-title":"Learning transferable visual models from natural language supervision","volume-title":"ICML","author":"Radford","year":"2021"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref38","article-title":"RORD: A real-world object removal dataset","volume-title":"BMVC","author":"Sagong","year":"2022"},{"key":"ref39","article-title":"LAION-5B: an open large-scale dataset for training next generation image-text models","volume-title":"NeurIPS","author":"Schuhmann","year":"2022"},{"key":"ref40","article-title":"Carvekit: Automated high-quality background removal framework","author":"Selin","year":"2023"},{"key":"ref41","article-title":"Large-scale text-to-image model with inpainting is a zero-shot subject-driven image generator","author":"Shin","year":"2024","journal-title":"arXiv"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01756"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00769"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/WACV51458.2022.00323"},{"key":"ref45","article-title":"Ominicontrol: Minimal and universal control for diffusion transformer","author":"Tan","year":"2024","journal-title":"arXiv"},{"key":"ref46","article-title":"Flux-controlnet-inpainting","year":"2024"},{"key":"ref47","article-title":"Add-it: Training-free object insertion in images with pretrained diffusion models","author":"Tewel","year":"2024","journal-title":"arXiv"},{"key":"ref48","article-title":"Magic: Multi-modality guided image completion","volume-title":"ICLR","author":"Wang","year":"2024"},{"key":"ref49","article-title":"Metashadow: Objectcentered shadow detection, removal, and synthesis","author":"Wang","year":"2024","journal-title":"arXiv"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72980-5_7"},{"key":"ref51","article-title":"Objectmate: A recurrence prior for object insertion and subject-driven generation","author":"Winter","year":"2024","journal-title":"arXiv"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00678"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01763"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73668-1_10"},{"key":"ref55","doi-asserted-by":"crossref","DOI":"10.1109\/CVPRW56347.2022.00126","article-title":"MANIQA: multi-dimension attention network for noreference image quality assessment","volume-title":"CVPR Workshops","author":"Yang","year":"2022"},{"key":"ref56","article-title":"Magicremover: Tuning-free text-guided image inpainting with diffusion models","author":"Yang","year":"2023","journal-title":"arXiv"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19787-1_38"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19787-1_14"},{"key":"ref59","article-title":"Promptfix: You prompt and we fix the photo","volume-title":"NeurIPS","author":"Yu","year":"2024"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00068"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19787-1_16"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.244"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73636-0_12"}],"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\/11445063.pdf?arnumber=11445063","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T06:46:38Z","timestamp":1777531598000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11445063\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":63,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01609","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}