{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,13]],"date-time":"2026-10-13T17:03:34Z","timestamp":1791911014065,"version":"4.3.4"},"reference-count":83,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"10","license":[{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Tencent University Relations Tencent AI Lab","award":["RBFR2024006"],"award-info":[{"award-number":["RBFR2024006"]}]},{"name":"Key Research and Development Program of Pengcheng Laboratory","award":["PCL2024A02"],"award-info":[{"award-number":["PCL2024A02"]}]},{"name":"Guangdong Provincial Key Laboratory of Ultra High Definition Immersive Media Technology","award":["2024B1212010006"],"award-info":[{"award-number":["2024B1212010006"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2026,10]]},"DOI":"10.1109\/tpami.2026.3695011","type":"journal-article","created":{"date-parts":[[2026,5,19]],"date-time":"2026-05-19T19:49:41Z","timestamp":1779220181000},"page":"11746-11757","source":"Crossref","is-referenced-by-count":2,"title":["BrushEdit: All-in-One Image Inpainting and Editing"],"prefix":"10.1109","volume":"48","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-7325-6439","authenticated-orcid":false,"given":"Yaowei","family":"Li","sequence":"first","affiliation":[{"name":"Peking University","place":["Shenzhen, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuxuan","family":"Bian","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0668-1375","authenticated-orcid":false,"given":"Xuan","family":"Ju","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhaoyang","family":"Zhang","sequence":"additional","affiliation":[{"name":"Tencent PCG","place":["Shenzhen, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1642-0750","authenticated-orcid":false,"given":"Junhao","family":"Zhuang","sequence":"additional","affiliation":[{"name":"Tsinghua University","place":["Beijing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7673-8325","authenticated-orcid":false,"given":"Ying","family":"Shan","sequence":"additional","affiliation":[{"name":"Tencent PCG","place":["Shenzhen, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9999-6140","authenticated-orcid":false,"given":"Yuexian","family":"Zou","sequence":"additional","affiliation":[{"name":"Peking University","place":["Shenzhen, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6747-126X","authenticated-orcid":false,"given":"Qiang","family":"Xu","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Ho"},{"key":"ref2","article-title":"Denoising diffusion implicit models","author":"Song","year":"2020"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref4","article-title":"EMU: Enhancing image generation models using photogenic needles in a haystack","author":"Dai","year":"2023"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00763"},{"key":"ref6","article-title":"Prompt-to-prompt image editing with cross-attention control","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Hertz"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02062"},{"key":"ref8","article-title":"SDEdit: Guided image synthesis and editing with stochastic differential equations","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Meng"},{"key":"ref9","article-title":"PnP inversion: Boosting diffusion-based editing with 3 lines of code","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Ju"},{"key":"ref10","article-title":"Inversion-free image editing with natural language","author":"Xu","year":"2023"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01764"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01208"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00799"},{"key":"ref14","article-title":"Guiding instruction-based image editing via multimodal large language models","author":"Fu","year":"2023"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.01220"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.52202\/079017-4077"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01767"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3592450"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02148"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73636-0_12"},{"key":"ref21","article-title":"HD-painter: High-resolution and prompt-faithful text-guided image inpainting with diffusion models","author":"Manukyan","year":"2023"},{"key":"ref22","article-title":"Replaceanything as you want: Ultra-high quality content replacement","author":"Binghui","year":"2023"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01761"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2025.3541625"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00925"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19787-1_16"},{"key":"ref28","article-title":"Large scale image completion via co-modulated generative adversarial networks","author":"Zhao","year":"2021"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00621"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0714"},{"key":"ref31","article-title":"Fine-grained image editing by pixel-wise guidance using diffusion models","author":"Matsunaga","year":"2022"},{"key":"ref32","first-page":"48723","article-title":"ImageBrush: Learning visual in-context instructions for exemplar-based image manipulation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Yang"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.00844"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1145\/3588432.3591500"},{"key":"ref35","article-title":"FlexEdit: Flexible and controllable diffusion-based object-centric image editing","author":"Nguyen","year":"2024"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-023-01977-6"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.3390\/app132011189"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1145\/344779.344972"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2004.833105"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00153"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01063"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01117"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-demo.25"},{"key":"ref44","article-title":"Image inpainting via tractable steering of diffusion models","author":"Liu","year":"2023"},{"key":"ref45","article-title":"Classifier-free diffusion guidance","author":"Ho","year":"2022"},{"key":"ref46","article-title":"Towards coherent image inpainting using denoising diffusion implicit models","author":"Zhang","year":"2023"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00428"},{"key":"ref48","article-title":"Magicremover: Tuning-free text-guided image inpainting with diffusion models","author":"Yang","year":"2023"},{"key":"ref49","article-title":"Diffusers: State-of-the-art diffusion models","author":"von Platen","year":"2022"},{"key":"ref50","article-title":"DreamInpainter: Text-guided subject-driven image inpainting with diffusion models","author":"Xie","year":"2023"},{"key":"ref51","article-title":"Inpaint anything: Segment anything meets image inpainting","author":"Yu","year":"2023"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612200"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00582"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1145\/3592451"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/wacv57701.2024.00424"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1145\/3588432.3591513"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00191"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1336"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02078"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00189"},{"key":"ref61","article-title":"SEGA: Instructing diffusion using semantic dimensions","author":"Brack","year":"2023"},{"key":"ref62","article-title":"LEDITS: Real image editing with DDPM inversion and semantic guidance","author":"Tsaban","year":"2023"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00683"},{"key":"ref64","article-title":"Unifying diffusion models\u2019 latent space, with applications to cyclediffusion and guidance","author":"Wu","year":"2022"},{"key":"ref65","article-title":"DiffEdit: Diffusion-based semantic image editing with mask guidance","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Couairon"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00584"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/wacv57701.2024.00792"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00246"},{"key":"ref69","first-page":"16784","article-title":"GLIDE: Towards photorealistic image generation and editing with text-guided diffusion models","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Nichol"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.01208"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72661-3_9"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1833"},{"key":"ref73","article-title":"Grounded SAM: Assembling open-world models for diverse visual tasks","author":"Ren","year":"2024"},{"key":"ref74","article-title":"Peak signal-to-noise ratio\u2013Wikipedia, the free encyclopedia","year":"2024"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00068"},{"key":"ref76","article-title":"Mean squared error\u2013Wikipedia, the free encyclopedia","year":"2024"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2003.819861"},{"key":"ref78","article-title":"GODIVA: Generating open-domain videos from natural descriptions","author":"Wu","year":"2021"},{"key":"ref79","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford"},{"key":"ref80","article-title":"DINOv2: Learning robust visual features without supervision","author":"Oquab","year":"2023"},{"key":"ref81","article-title":"Qwen2-VL: Enhancing vision-language model\u2019s perception of the world at any resolution","author":"Wang","year":"2024"},{"key":"ref82","article-title":"Qwen3-VL technical report","author":"Bai","year":"2025"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01458"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/34\/11674301\/11524208.pdf?arnumber=11524208","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,24]],"date-time":"2026-09-24T17:27:50Z","timestamp":1790270870000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11524208\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,10]]},"references-count":83,"journal-issue":{"issue":"10"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2026.3695011","relation":{},"ISSN":["0162-8828","2160-9292","1939-3539"],"issn-type":[{"value":"0162-8828","type":"print"},{"value":"2160-9292","type":"electronic"},{"value":"1939-3539","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,10]]}}}