DreamMix: Decoupling Object Attributes for Enhanced Editability in Customized Image Inpainting
Yicheng Yang, Pengxiang Li, Lu Zhang, Liqian Ma, Ping Hu, Siyu Du, Yunzhi Zhuge, Xu Jia, Huchuan Lu

TL;DR
DreamMix is a diffusion-based image inpainting framework that effectively separates object attributes from identity, enabling more controllable and editable image modifications while preserving original identities.
Contribution
It introduces a novel attribute decoupling mechanism, textual attribute substitution, and a disentangled inpainting framework to improve attribute editability and identity preservation.
Findings
Outperforms existing methods in attribute editing and object insertion tasks.
Achieves a better balance between identity preservation and attribute flexibility.
Demonstrates versatility across various inpainting applications.
Abstract
Subject-driven image inpainting has recently gained prominence in image editing with the rapid advancement of diffusion models. Beyond image guidance, recent studies have explored incorporating text guidance to achieve identity-preserved yet locally editable object inpainting. However, these methods still suffer from identity overfitting, where original attributes remain entangled with target textual instructions. To overcome this limitation, we propose DreamMix, a diffusion-based framework adept at inserting target objects into user-specified regions while concurrently enabling arbitrary text-driven attribute modifications. DreamMix introduces three key components: (i) an Attribute Decoupling Mechanism (ADM) that synthesizes diverse attribute-augmented image-text pairs to mitigate overfitting; (ii) a Textual Attribute Substitution (TAS) module that isolates target attributes via…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsGenerative Adversarial Networks and Image Synthesis · Computer Graphics and Visualization Techniques · 3D Shape Modeling and Analysis
MethodsDiffusion · Inpainting · Focus
