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

• URL: http://arxiv.org/abs/2606.25907v1
• Date: Wed, 24 Jun 2026 14:55:07 GMT
• Title: In-context Region-based Drag: Drag Any Region to Any Shape
• Abstract summary: This paper focuses on region-based drag and introduces a novel In-Context Region-based Drag (ICRDrag) method.<n>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.<n>Experiments show that ICRDrag significantly outperforms existing methods in both quantitative metrics and user studies.
• Score: 58.32054552329584
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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.

Related papers

• Can Image Splicing and Copy-Move Forgery Be Detected by the Same Model? Forensim: An Attention-Based State-Space Approach [8.024142807011378]
  Forensim is an attention-based state-space framework for image forgery detection.<n>It jointly localizes both manipulated (target) and source regions.<n>Forensim achieves state-of-the-art performance on standard benchmarks.
  arXiv  Detail & Related papers  (2026-02-10T18:46:04Z)
• ContextDrag: Precise Drag-Based Image Editing via Context-Preserving Token Injection and Position-Consistent Attention [81.12932992203885]
  We introduce ContextDrag, a new paradigm for drag-based editing.<n>By incorporating VAE-encoded features from the reference image, ContextDrag can leverage rich contextual cues and preserve fine-grained details.
  arXiv  Detail & Related papers  (2025-12-09T10:51:45Z)
• Detect an Object At Once without Fine-tuning [24.580732053747568]
  It consists of two phases: (1) generating a Similarity Density Map (SDM) by convolving the scene image with the given object image patch(es) so that the highlight areas in the SDM indicate the possible locations; (2) obtaining the object occupied areas in the scene through a Region Alignment Network (RAN) The RAN is constructed on a backbone of Deep Siamese Network (DSN), and different from the traditional DSNs, it aims to obtain the object accurate regions by regressing the location and area differences between the ground truths and the predicted ones indicated by the highlight areas in SDM.
  arXiv  Detail & Related papers  (2024-11-04T15:38:32Z)
• RegionDrag: Fast Region-Based Image Editing with Diffusion Models [14.65208340413507]
  RegionDrag is a copy-and-paste dragging method that allows users to express their editing instructions in the form of handle and target regions. RegionDrag completes the edit on an image with a resolution of 512x512 in less than 2 seconds, which is more than 100x faster than DragDiffusion.
  arXiv  Detail & Related papers  (2024-07-25T17:59:13Z)
• LIME: Localized Image Editing via Attention Regularization in Diffusion Models [69.33072075580483]
  This paper introduces LIME for localized image editing in diffusion models.<n>LIME does not require user-specified regions of interest (RoI) or additional text input, but rather employs features from pre-trained methods and a straightforward clustering method to obtain precise editing mask.<n>We propose a novel cross-attention regularization technique that penalizes unrelated cross-attention scores in the RoI during the denoising steps, ensuring localized edits.
  arXiv  Detail & Related papers  (2023-12-14T18:59:59Z)
• DragDiffusion: Harnessing Diffusion Models for Interactive Point-based Image Editing [94.24479528298252]
  DragGAN is an interactive point-based image editing framework that achieves impressive editing results with pixel-level precision. By harnessing large-scale pretrained diffusion models, we greatly enhance the applicability of interactive point-based editing on both real and diffusion-generated images. We present a challenging benchmark dataset called DragBench to evaluate the performance of interactive point-based image editing methods.
  arXiv  Detail & Related papers  (2023-06-26T06:04:09Z)
• Region-Aware Diffusion for Zero-shot Text-driven Image Editing [78.58917623854079]
  We propose a novel region-aware diffusion model (RDM) for entity-level image editing. To strike a balance between image fidelity and inference speed, we design the intensive diffusion pipeline. The results show that RDM outperforms the previous approaches in terms of visual quality, overall harmonization, non-editing region content preservation, and text-image semantic consistency.
  arXiv  Detail & Related papers  (2023-02-23T06:20:29Z)
• RPCL: A Framework for Improving Cross-Domain Detection with Auxiliary Tasks [74.10747285807315]
  Cross-Domain Detection (XDD) aims to train an object detector using labeled image from a source domain but have good performance in the target domain with only unlabeled images. This paper provides a complementary solution to align domains by learning the same auxiliary tasks in both domains simultaneously.
  arXiv  Detail & Related papers  (2021-04-18T02:56:19Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.