BindEdit: Taming Attention Leakage for Precise Multi-Object Image Editing

• URL: http://arxiv.org/abs/2606.18906v1
• Date: Wed, 17 Jun 2026 10:32:14 GMT
• Title: BindEdit: Taming Attention Leakage for Precise Multi-Object Image Editing
• Abstract summary: Real image editing enables precise manipulation of visual content, yet existing methods often fail in complex multi-object scenarios.<n>We propose BindEdit, which enforces attention-level constraints within a single diffusion trajectory.<n>BindEdit consistently outperforms existing methods within a single diffusion trajectory.
• Score: 8.542586773614113
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Real image editing enables precise manipulation of visual content, yet existing methods often fail in complex multi-object scenarios, causing semantic blending, object duplication, or incomplete edits. We attribute these failures to attention leakage, where signals across spatial regions and text tokens become entangled during the denoising process. Specifically, we identify two distinct forms of leakage: Edit-Token Leakage, where ambiguous token-region alignment leads to object blending, and Source Dominance Leakage, where tokens of unchanged source objects overwhelm the attention intended for target entities. To resolve these leakages, we propose \textbf{BindEdit}, which enforces attention-level constraints within a single diffusion trajectory. To suppress Edit-Token Leakage, BindEdit jointly regularizes cross- and self-attention so that each target token group is bound to its corresponding spatial region while maintaining instance-level separation. To suppress Source Dominance Leakage, a cross-attention re-balancing mechanism amplifies target token influence and attenuates residual source semantics within editable regions. Moreover, a region fidelity term ensures that each target concept is expressed coherently across the entire editing mask. Additionally, we propose a comprehensive multi-object benchmark encompassing diverse object counts and categories. Extensive experiments demonstrate that BindEdit consistently outperforms existing methods within a single diffusion trajectory, maintaining robust performance across both single- and multi-object editing scenarios.

Related papers

• PC-Edit: Prompt-Contrastive Region Discovery and Region-Guided Editing [6.411145731142763]
  PC-Edit is a prompt-contrastive framework for training-free MM-DiT editing.<n>We show that PC-Edit achieves the best editing quality and background preservation among methods without user-specified edit regions.
  arXiv  Detail & Related papers  (2026-07-23T13:42:03Z)
• OcclusionFormer: Arranging Z-Order for Layout-Grounded Image Generation [49.49933361280724]
  We introduce OcclusionFormer, a novel framework that explicitly models Z-order priority by decoupling instances.<n>We also introduce a queried alignment loss that explicitly supervises individual instances and enhances semantic consistency.<n>The proposed method effectively reduces ambiguity in overlapping regions, enforces correct occlusion dependencies, and preserves structural integrity, leading to substantial accuracy gains across diverse scenes.
  arXiv  Detail & Related papers  (2026-05-20T16:10:44Z)
• Drag within Prior Distribution: Text-Conditioned Point-Based Image Editing within Distribution Constraints [7.503616785263929]
  Diffusion-based point editing can manipulate image semantics and fine details by applying localized perturbations on the manifold of noise latent perturbations.<n>Traditional point-based editing relies on pairs of handle and target points to define motion trajectories.<n>We introduce a CLIP-based model to evaluate and guide intermediate editing steps, ensuring that the generated results remain both semantically aligned.
  arXiv  Detail & Related papers  (2026-05-13T11:05:31Z)
• Shifting the Breaking Point of Flow Matching for Multi-Instance Editing [47.32746672482526]
  We introduce Instance-Disentangled Attention, a mechanism that partitions joint attention operations and enforces binding between instance-specific textual instructions and spatial regions.<n>Our approach promotes edit disentanglement and locality while preserving global output coherence, enabling single-pass, instance-level editing.
  arXiv  Detail & Related papers  (2026-02-09T14:52:45Z)
• SAEdit: Token-level control for continuous image editing via Sparse AutoEncoder [52.754326452329956]
  We introduce a method for disentangled and continuous editing through token-level manipulation of text embeddings.<n>The edits are applied by manipulating the embeddings along carefully chosen directions, which control the strength of the target attribute.<n>Our method operates directly on text embeddings without modifying the diffusion process, making it model agnostic and broadly applicable to various image backbones.
  arXiv  Detail & Related papers  (2025-10-06T17:51:04Z)
• MDE-Edit: Masked Dual-Editing for Multi-Object Image Editing via Diffusion Models [10.798205956644317]
  We propose a training-free, inference-stage optimization approach that enables precise localized image manipulation in complex multi-object scenes, named MDE-Edit.<n>Extensive experiments demonstrate that MDE-Edit outperforms state-of-the-art methods in editing accuracy and visual quality, offering a robust solution for complex multi-object image manipulation tasks.
  arXiv  Detail & Related papers  (2025-05-08T10:01:14Z)
• Addressing Text Embedding Leakage in Diffusion-based Image Editing [33.1686050396517]
  We introduce Attribute-Leakage-free Editing (ALE), a framework that tackles attribute leakage at its source.<n>ALE combines Object-Restricted Embeddings (ORE) to disentangle text embeddings, Region-Guided Blending for Cross-Attention Masking (RGB-CAM) for spatially precise attention, and Background Blending (BB) to preserve non-edited content.
  arXiv  Detail & Related papers  (2024-12-06T02:10:07Z)
• DreamMix: Decoupling Object Attributes for Enhanced Editability in Customized Image Inpainting [56.77074226109392]
  We propose DreamMix, a diffusion-based framework adept at inserting target objects into user-specified regions.<n>We show that DreamMix achieves a superior balance between identity preservation and attribute editability across diverse applications.
  arXiv  Detail & Related papers  (2024-11-26T08:44:47Z)
• DiffUHaul: A Training-Free Method for Object Dragging in Images [78.93531472479202]
  We propose a training-free method, dubbed DiffUHaul, for the object dragging task. We first apply attention masking in each denoising step to make the generation more disentangled across different objects. In the early denoising steps, we interpolate the attention features between source and target images to smoothly fuse new layouts with the original appearance.
  arXiv  Detail & Related papers  (2024-06-03T17:59:53Z)
• EVA: Zero-shot Accurate Attributes and Multi-Object Video Editing [62.15822650722473]
  Current video editing methods fail to edit the foreground and background simultaneously while preserving the original layout. We introduce EVA, a textbfzero-shot and textbfmulti-attribute video editing framework tailored for human-centric videos with complex motions. EVA can be easily generalized to multi-object editing scenarios and achieves accurate identity mapping.
  arXiv  Detail & Related papers  (2024-03-24T12:04:06Z)

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.