DreamMix：解耦物件屬性以提升客製化影像修補的編輯能力

摘要

隨著擴散模型的最新進展，主體驅動的圖像修復已成為圖像編輯領域的熱門任務。現有方法主要側重於身份特徵保留，但難以維持插入物件的可編輯性。為此，本文提出DreamMix——一種基於擴散機制的生成模型，既能將目標物件插入使用者指定位置的場景中，又能同步實現對其屬性的任意文本驅動修改。具體而言，我們利用先進的基礎修復模型，引入解耦的局部-全局修復框架，以平衡精準的局部物件插入與有效的全局視覺連貫性。此外，我們提出屬性解耦機制（ADM）與文本屬性替換（TAS）模組，分別提升文本屬性引導的多樣性與判別能力。大量實驗表明，DreamMix在物件插入、屬性編輯和小物件修復等多種應用場景中，能有效平衡身份特徵保留與屬性可編輯性。我們的程式碼已公開於https://github.com/mycfhs/DreamMix。

English

Subject-driven image inpainting has emerged as a popular task in image editing alongside recent advancements in diffusion models. Previous methods primarily focus on identity preservation but struggle to maintain the editability of inserted objects. In response, this paper introduces DreamMix, a diffusion-based generative model adept at inserting target objects into given scenes at user-specified locations while concurrently enabling arbitrary text-driven modifications to their attributes. In particular, we leverage advanced foundational inpainting models and introduce a disentangled local-global inpainting framework to balance precise local object insertion with effective global visual coherence. Additionally, we propose an Attribute Decoupling Mechanism (ADM) and a Textual Attribute Substitution (TAS) module to improve the diversity and discriminative capability of the text-based attribute guidance, respectively. Extensive experiments demonstrate that DreamMix effectively balances identity preservation and attribute editability across various application scenarios, including object insertion, attribute editing, and small object inpainting. Our code is publicly available at https://github.com/mycfhs/DreamMix.

DreamMix：解耦物件屬性以提升客製化影像修補的編輯能力

DreamMix: Decoupling Object Attributes for Enhanced Editability in Customized Image Inpainting

摘要

Support