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

2024-11-26 · Yicheng Yang, Pengxiang Li, Lu Zhang, Liqian Ma, Ping Hu, Siyu Du, Yunzhi Zhuge, Xu Jia, Huchuan Lu

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.

📄 PDF Abstract BibTeX arXiv:2411.17223

Code (1)

mycfhs/dreammix 공식 구현 pytorch

Tasks

AttributeDiversityImage InpaintingObject

Methods 이 논문이 사용한 방법론

Diffusion Diffusion models generate samples by gradually removing noise from a signal, and their training objective can be expressed as a reweighted variational lower-bound…

Inpainting Train a convolutional neural network to generate the contents of an arbitrary image region conditioned on its surroundings.

Focus 설명 없음

SVGDreamer++: Advancing Editability and Diversity in Text-Guided SVG Generation

2024-11-26 · XiMing Xing, Qian Yu, Chuang Wang, Haitao Zhou 외

Recently, text-guided scalable vector graphics (SVG) synthesis has demonstrated significant potential in domains such as iconography and sketching. However, SVGs generated from existing Text-to-SVG methods often lack edi…

Diversity Image Segmentation Semantic Segmentation Vector Graphics

Learning Single/Multi-Attribute of Object with Symmetry and Group

2021-10-09 · Yong-Lu Li, Yue Xu, Xinyu Xu, Xiaohan Mao 외

Attributes and objects can compose diverse compositions. To model the compositional nature of these concepts, it is a good choice to learn them as transformations, e.g., coupling and decoupling. However, complex transfor…

Attribute Compositional Zero-Shot Learning Zero-Shot Learning

Consistent and Editable: A Balanced Framework for Text-Guided Video Editing

2026-07-06 · Tao Jin, Li Xiao arxiv

Recently, diffusion models have achieved considerable success in the text-guided video editing domain. However, existing works often struggle to balance the trade-off between temporal consistency and editability in video…

Symmetry and Group in Attribute-Object Compositions

2020-04-01 · CVPR 2020 6 · Yong-Lu Li, Yue Xu, Xiaohan Mao, Cewu Lu

Attributes and objects can compose diverse compositions. To model the compositional nature of these general concepts, it is a good choice to learn them through transformations, such as coupling and decoupling. However, c…

Attribute Compositional Zero-Shot Learning Object Zero-Shot Learning

AmodalSVG: Amodal Image Vectorization via Semantic Layer Peeling

2026-04-13 · Juncheng Hu, Ziteng Xue, Guotao Liang, Anran Qi 외 arxiv

We introduce AmodalSVG, a new framework for amodal image vectorization that produces semantically organized and geometrically complete SVG representations from natural images. Existing vectorization methods operate under…