paper-with-me

홈 › Papers

In-context Region-based Drag: Drag Any Region to Any Shape

2026-06-24 · Jiacheng Sui, Tianyu Hao, Bingjie Gao, Li Niu, Guangtao Zhai arxiv

Diffusion models have shown promise in drag-style editing. Previous works mainly focus on point-based drag, which is inherently ambiguous. This paper focuses on region-based drag and introduces a novel In-Context Region-based Drag (ICRDrag) method. Under the in-context learning framework, ICRDrag consumes a source image, a source region mask, and a target region mask, producing the target dragged image. Built upon the basic in-context learning model, we introduce two novel attention regularization: 1) image-mask attention consistency to ensure that a target region attends to similar source regions for image and mask modalities; 2) source-target attention correspondence to ensure the mutual correspondence between source and target regions. To facilitate region-based drag, we also construct Paired Region Dataset (PRD), a large-scale dataset with paired masks and images. Extensive experiments show that ICRDrag significantly outperforms existing methods in both quantitative metrics and user studies, achieving superior editing accuracy and visual fidelity. The dataset, code, and model are available at https://github.com/bcmi/ICRDrag-Region-Drag-Editing.

📄 PDF Abstract BibTeX arXiv:2606.25907

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

RegionDrag: Fast Region-Based Image Editing with Diffusion Models

2024-07-25 · Jingyi Lu, Xinghui Li, Kai Han

Point-drag-based image editing methods, like DragDiffusion, have attracted significant attention. However, point-drag-based approaches suffer from computational overhead and misinterpretation of user intentions due to th…

DragFlow: Unleashing DiT Priors with Region Based Supervision for Drag Editing

2025-10-02 · Zihan Zhou, Shilin Lu, Shuli Leng, Shaocong Zhang 외 arxiv

Drag-based image editing has long suffered from distortions in the target region, largely because the priors of earlier base models, Stable Diffusion, are insufficient to project optimized latents back onto the natural i…

Image Editing

ContextDrag: Precise Drag-Based Image Editing via Context-Preserving Token Injection and Position-Aligned Attention

2025-12-09 · Huiguo He, Pengyu Yan, Ziqi Yi, Weizhi Zhong 외 arxiv

Drag-based image editing enables intuitive visual manipulation through point-based drag operations. Existing methods mainly rely on diffusion inversion or pixel-space warping with inpainting. However, inversion inherentl…

Image Editing

Inpaint4Drag: Repurposing Inpainting Models for Drag-Based Image Editing via Bidirectional Warping

2025-09-04 · Jingyi Lu, Kai Han arxiv

Drag-based image editing has emerged as a powerful paradigm for intuitive image manipulation. However, existing approaches predominantly rely on manipulating the latent space of generative models, leading to limited prec…

Image ManipulationImage InpaintingImage Editing

TextDragon: An End-to-End Framework for Arbitrary Shaped Text Spotting

2019-10-01 · ICCV 2019 10 · Wei Feng, Wenhao He, Fei Yin, Xu-Yao Zhang 외

Most existing text spotting methods either focus on horizontal/oriented texts or perform arbitrary shaped text spotting with character-level annotations. In this paper, we propose a novel text spotting framework to detec…

Text DetectionText Spotting