AdaEraser: Training-Free Object Removal via Adaptive Attention Suppression

• URL: http://arxiv.org/abs/2605.15921v1
• Date: Fri, 15 May 2026 13:03:42 GMT
• Title: AdaEraser: Training-Free Object Removal via Adaptive Attention Suppression
• Abstract summary: We propose AdaEraser, an adaptive framework that modulates attention based on the estimated presence of target object concepts.<n>AdaEraser achieves superior performance in object removal, outperforming even training-based methods.
• Score: 0.40611352512781856
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Object removal aims to eliminate specified objects from images while plausibly inpainting the affected regions with background content. Current training-free methods typically block attention to object regions within self-attention layers during the image generation process, leveraging surrounding background information to restore the image. However, indiscriminate suppression of self-attention in the vacated areas can degrade generation quality, as the model must simultaneously reconstruct background content in these regions. To solve this conflict, we propose AdaEraser, an adaptive framework that dynamically modulates attention based on the estimated presence of target object concepts. Through analysis of self-attention map evolution across denoising timesteps before and during removal, we develop a token-wise adaptive attention suppression strategy. This approach enables progressive perception of object removal throughout the denoising process, with the suppression strength in self-attention layers adjusted adaptively. Extensive experiments demonstrate that AdaEraser achieves superior performance in object removal, outperforming even training-based methods.

Related papers

• PANDORA: Pixel-wise Attention Dissolution and Latent Guidance for Zero-Shot Object Removal [18.565422674751215]
  We propose a novel zero-shot object removal framework, namely PANDORA, that operates directly on pre-trained text-to-image diffusion models.<n>We propose Pixel-wise Attention Dissolution to remove object by nullifying the most correlated attention keys for masked pixels.<n>We further introduce Localized Attentional Disentanglement Guidance to steer denoising toward latent manifold favorable to clean object removal.
  arXiv  Detail & Related papers  (2026-03-29T07:34:08Z)
• Active Adversarial Noise Suppression for Image Forgery Localization [56.98050814363447]
  We introduce an Adversarial Noise Suppression Module (ANSM) that generate a defensive perturbation to suppress the attack effect of adversarial noise.<n>To our best knowledge, this is the first report of adversarial defense in image forgery localization tasks.
  arXiv  Detail & Related papers  (2025-06-15T14:53:27Z)
• 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)
• Erase Diffusion: Empowering Object Removal Through Calibrating Diffusion Pathways [13.08168394252538]
  Erase inpainting aims to precisely remove target objects within masked regions while preserving the overall consistency of the surrounding content.<n>We propose a novel Erase Diffusion, termed EraDiff, aimed at unleashing the potential power of standard diffusion in the context of object removal.<n>Our proposed EraDiff achieves state-of-the-art performance on the OpenImages V5 dataset and demonstrates significant superiority in real-world scenarios.
  arXiv  Detail & Related papers  (2025-03-10T08:06:51Z)
• Attentive Eraser: Unleashing Diffusion Model's Object Removal Potential via Self-Attention Redirection Guidance [10.625932330968409]
  Attentive Eraser is a tuning-free method to empower pre-trained diffusion models for stable and effective object removal.<n>We introduce Attention Activation and Suppression (ASS), which re-engineers the self-attention mechanism.<n>We also introduce Self-Attention Redirection Guidance (SARG), which utilizes the self-attention redirected by ASS to guide the generation process.
  arXiv  Detail & Related papers  (2024-12-17T14:56:59Z)
• Learning Flow Fields in Attention for Controllable Person Image Generation [59.10843756343987]
  Controllable person image generation aims to generate a person image conditioned on reference images.<n>We propose learning flow fields in attention (Leffa), which explicitly guides the target query to attend to the correct reference key.<n>Leffa achieves state-of-the-art performance in controlling appearance (virtual try-on) and pose (pose transfer), significantly reducing fine-grained detail distortion.
  arXiv  Detail & Related papers  (2024-12-11T15:51:14Z)
• TALE: Training-free Cross-domain Image Composition via Adaptive Latent Manipulation and Energy-guided Optimization [59.412236435627094]
  TALE is a training-free framework harnessing the generative capabilities of text-to-image diffusion models. We equip TALE with two mechanisms dubbed Adaptive Latent Manipulation and Energy-guided Latent Optimization. Our experiments demonstrate that TALE surpasses prior baselines and attains state-of-the-art performance in image-guided composition.
  arXiv  Detail & Related papers  (2024-08-07T08:52:21Z)
• Denoising as Adaptation: Noise-Space Domain Adaptation for Image Restoration [64.84134880709625]
  We show that it is possible to perform domain adaptation via the noise space using diffusion models.<n>In particular, by leveraging the unique property of how auxiliary conditional inputs influence the multi-step denoising process, we derive a meaningful diffusion loss.<n>We present crucial strategies such as channel-shuffling layer and residual-swapping contrastive learning in the diffusion model.
  arXiv  Detail & Related papers  (2024-06-26T17:40:30Z)
• 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)

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.