{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,18]],"date-time":"2026-03-18T02:46:45Z","timestamp":1773802005511,"version":"3.50.1"},"reference-count":0,"publisher":"Association for the Advancement of Artificial Intelligence (AAAI)","issue":"14","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["AAAI"],"abstract":"<jats:p>Recent diffusion-based models have significantly improved inpainting quality.\nHowever, existing methods struggle with multi-task inpainting due to conflicting optimization objectives, and current datasets are typically limited to task-specific scenarios, hindering joint training.\nTo address these challenges, we propose MagicPaint, a unified diffusion-based inpainting model that supports object addition, removal, and unconditional inpainting across both text and image modalities.\nMagicPaint semantically decouples operation types and target content by learnable tokens in MMToken Module, effectively reconciling conflicting optimization objectives and enabling robust multi-task, multi-modal inpainting.\nBesides, a novel inpainting paradigm named MagicMask, encodes operating intent directly into the mask and applies a mask loss for spatially precise supervision.\nIn addition, existing inpainting datasets are insufficient for multi-task and multi-modal scenarios, limiting the capability of inpainting models. Thus, we further introduce\na new dataset comprising 2.1M image tuples. It is dedicatedly designed to support diverse inpainting scenarios and significantly improves upon existing datasets, particularly in object removal. \nThrough efforts from both model and data perspectives, MagicPaint enables users to operate anything\u2014add, remove or inpaint content which is specified through either text or image modalities in a seamless and unified manner.\nExtensive experiments demonstrate that MagicPaint achieves state-of-the-art performance across three key tasks (i.e., text-guided addition, image-guided addition, and object removal) and produces outputs with superior visual consistency and contextual fidelity compared to existing methods.<\/jats:p>","DOI":"10.1609\/aaai.v40i14.38151","type":"journal-article","created":{"date-parts":[[2026,3,18]],"date-time":"2026-03-18T00:09:16Z","timestamp":1773792556000},"page":"11667-11675","source":"Crossref","is-referenced-by-count":0,"title":["MagicPaint: Operate Anything for Image Inpainting with Diffusion Model"],"prefix":"10.1609","volume":"40","author":[{"given":"Qinhong","family":"Yang","sequence":"first","affiliation":[]},{"given":"Dongdong","family":"Chen","sequence":"additional","affiliation":[]},{"given":"Qi","family":"Chu","sequence":"additional","affiliation":[]},{"given":"Tao","family":"Gong","sequence":"additional","affiliation":[]},{"given":"Qiankun","family":"Liu","sequence":"additional","affiliation":[]},{"given":"Zhentao","family":"Tan","sequence":"additional","affiliation":[]},{"given":"Xulin","family":"Li","sequence":"additional","affiliation":[]},{"given":"Huamin","family":"Feng","sequence":"additional","affiliation":[]},{"given":"Nenghai","family":"Yu","sequence":"additional","affiliation":[]}],"member":"9382","published-online":{"date-parts":[[2026,3,14]]},"container-title":["Proceedings of the AAAI Conference on Artificial Intelligence"],"original-title":[],"link":[{"URL":"https:\/\/ojs.aaai.org\/index.php\/AAAI\/article\/download\/38151\/42113","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/ojs.aaai.org\/index.php\/AAAI\/article\/download\/38151\/42113","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,18]],"date-time":"2026-03-18T00:09:16Z","timestamp":1773792556000},"score":1,"resource":{"primary":{"URL":"https:\/\/ojs.aaai.org\/index.php\/AAAI\/article\/view\/38151"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,14]]},"references-count":0,"journal-issue":{"issue":"14","published-online":{"date-parts":[[2026,3,17]]}},"URL":"https:\/\/doi.org\/10.1609\/aaai.v40i14.38151","relation":{},"ISSN":["2374-3468","2159-5399"],"issn-type":[{"value":"2374-3468","type":"electronic"},{"value":"2159-5399","type":"print"}],"subject":[],"published":{"date-parts":[[2026,3,14]]}}}