MDE-Edit: Masked Dual-Editing for Multi-Object Image Editing via Diffusion Models

• URL: http://arxiv.org/abs/2505.05101v2
• Date: Mon, 12 May 2025 01:42:39 GMT
• Title: MDE-Edit: Masked Dual-Editing for Multi-Object Image Editing via Diffusion Models
• Authors: Hongyang Zhu, Haipeng Liu, Bo Fu, Yang Wang,
• Abstract summary: 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.
• Score: 10.798205956644317
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Multi-object editing aims to modify multiple objects or regions in complex scenes while preserving structural coherence. This task faces significant challenges in scenarios involving overlapping or interacting objects: (1) Inaccurate localization of target objects due to attention misalignment, leading to incomplete or misplaced edits; (2) Attribute-object mismatch, where color or texture changes fail to align with intended regions due to cross-attention leakage, creating semantic conflicts (\textit{e.g.}, color bleeding into non-target areas). Existing methods struggle with these challenges: approaches relying on global cross-attention mechanisms suffer from attention dilution and spatial interference between objects, while mask-based methods fail to bind attributes to geometrically accurate regions due to feature entanglement in multi-object scenarios. To address these limitations, we propose a training-free, inference-stage optimization approach that enables precise localized image manipulation in complex multi-object scenes, named MDE-Edit. MDE-Edit optimizes the noise latent feature in diffusion models via two key losses: Object Alignment Loss (OAL) aligns multi-layer cross-attention with segmentation masks for precise object positioning, and Color Consistency Loss (CCL) amplifies target attribute attention within masks while suppressing leakage to adjacent regions. This dual-loss design ensures localized and coherent multi-object edits. 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.

Related papers

• CPAM: Context-Preserving Adaptive Manipulation for Zero-Shot Real Image Editing [24.68304617869157]
  Context-Preserving Adaptive Manipulation (CPAM) is a novel framework for complicated, non-rigid real image editing.<n>We develop a preservation adaptation module that adjusts self-attention mechanisms to preserve and independently control the object and background effectively.<n>We also introduce various mask-guidance strategies to facilitate diverse image manipulation tasks in a simple manner.
  arXiv  Detail & Related papers  (2025-06-23T09:19:38Z)
• ObjectClear: Complete Object Removal via Object-Effect Attention [56.2893552300215]
  We introduce a new dataset for OBject-Effect Removal, named OBER, which provides paired images with and without object effects, along with precise masks for both objects and their associated visual artifacts.<n>We propose a novel framework, ObjectClear, which incorporates an object-effect attention mechanism to guide the model toward the foreground removal regions by learning attention masks.<n>Experiments demonstrate that ObjectClear outperforms existing methods, achieving improved object-effect removal quality and background fidelity, especially in complex scenarios.
  arXiv  Detail & Related papers  (2025-05-28T17:51:17Z)
• Marmot: Multi-Agent Reasoning for Multi-Object Self-Correcting in Improving Image-Text Alignment [55.74860093731475]
  Marmot is a novel framework that employs Multi-Agent Reasoning for Multi-Object Self-Correcting.<n>We construct a multi-agent editing system featuring a decision-execution-verification mechanism.<n>Experiments demonstrate that Marmot significantly improves accuracy in object counting, attribute assignment, and spatial relationships.
  arXiv  Detail & Related papers  (2025-04-10T16:54:28Z)
• A Diffusion-Based Framework for Occluded Object Movement [39.6345172890042]
  We propose a Diffusion-based framework specifically designed for Occluded Object Movement, named DiffOOM.<n>The de-occlusion branch utilizes a background color-fill strategy and a continuously updated object mask to focus the diffusion process on completing the obscured portion of the target object.<n> Concurrently, the movement branch employs latent optimization to place the completed object in the target location and adopts local text-conditioned guidance to integrate the object into new surroundings appropriately.
  arXiv  Detail & Related papers  (2025-04-02T16:29:30Z)
• Addressing Attribute Leakages in Diffusion-based Image Editing without Training [18.85055192982783]
  ALE-Edit is a novel framework to minimize attribute leakage with three components.<n>We introduce ALE-Bench, a benchmark for evaluating attribute leakage with new metrics for target-external and target-internal leakage.
  arXiv  Detail & Related papers  (2024-12-06T02:10:07Z)
• ObjectRelator: Enabling Cross-View Object Relation Understanding Across Ego-Centric and Exo-Centric Perspectives [109.11714588441511]
  The Ego-Exo object correspondence task aims to understand object relations across ego-exo perspectives through segmentation.<n> PSALM, a recently proposed segmentation method, stands out as a notable exception with its demonstrated zero-shot ability on this task.<n>We propose ObjectRelator, a novel approach featuring two key modules: Multimodal Condition Fusion and SSL-based Cross-View Object Alignment.
  arXiv  Detail & Related papers  (2024-11-28T12:01:03Z)
• Unsupervised Modality Adaptation with Text-to-Image Diffusion Models for Semantic Segmentation [54.96563068182733]
  We propose Modality Adaptation with text-to-image Diffusion Models (MADM) for semantic segmentation task. MADM utilizes text-to-image diffusion models pre-trained on extensive image-text pairs to enhance the model's cross-modality capabilities. We show that MADM achieves state-of-the-art adaptation performance across various modality tasks, including images to depth, infrared, and event modalities.
  arXiv  Detail & Related papers  (2024-10-29T03:49:40Z)
• 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)
• LoMOE: Localized Multi-Object Editing via Multi-Diffusion [8.90467024388923]
  We introduce a novel framework for zero-shot localized multi-object editing through a multi-diffusion process. Our approach leverages foreground masks and corresponding simple text prompts that exert localized influences on the target regions. A combination of cross-attention and background losses within the latent space ensures that the characteristics of the object being edited are preserved.
  arXiv  Detail & Related papers  (2024-03-01T10:46:47Z)
• 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)

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.