PANDORA: Pixel-wise Attention Dissolution and Latent Guidance for Zero-Shot Object Removal

• URL: http://arxiv.org/abs/2603.27555v1
• Date: Sun, 29 Mar 2026 07:34:08 GMT
• Title: PANDORA: Pixel-wise Attention Dissolution and Latent Guidance for Zero-Shot Object Removal
• Abstract summary: 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.
• Score: 18.565422674751215
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Removing objects from natural images is challenging due to difficulty of synthesizing semantically coherent content while preserving background integrity. Existing methods often rely on fine-tuning, prompt engineering, or inference-time optimization, yet still suffer from texture inconsistency, rigid artifacts, weak foreground-background disentanglement, and poor scalability for multi-object removal. We propose a novel zero-shot object removal framework, namely PANDORA, that operates directly on pre-trained text-to-image diffusion models, requiring no fine-tuning, prompts, or optimization. We propose Pixel-wise Attention Dissolution to remove object by nullifying the most correlated attention keys for masked pixels, effectively eliminating the object from self-attention flow and allowing background context to dominate reconstruction. We further introduce Localized Attentional Disentanglement Guidance to steer denoising toward latent manifolds favorable to clean object removal. Together, these components enable precise, non-rigid, prompt-free, and scalable multi-object erasure in a single pass. Experiments demonstrate superior visual fidelity and semantic plausibility compared to state-of-the-art methods. The project page is available at https://vdkhoi20.github.io/PANDORA.

Related papers

• 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)
• OmniPaint: Mastering Object-Oriented Editing via Disentangled Insertion-Removal Inpainting [54.525583840585305]
  We introduce OmniPaint, a unified framework that re-conceptualizes object removal and insertion as interdependent processes.<n>Our novel CFD metric offers a robust, reference-free evaluation of context consistency and object hallucination.
  arXiv  Detail & Related papers  (2025-03-11T17:55:27Z)
• SmartEraser: Remove Anything from Images using Masked-Region Guidance [114.36809682798784]
  SmartEraser is built with a new removing paradigm called Masked-Region Guidance.<n>Masked-Region Guidance retains the masked region in the input, using it as guidance for the removal process.<n>We present Syn4Removal, a large-scale object removal dataset.
  arXiv  Detail & Related papers  (2025-01-14T17:55:12Z)
• OmniEraser: Remove Objects and Their Effects in Images with Paired Video-Frame Data [21.469971783624402]
  In this paper, we propose Video4Removal, a large-scale dataset comprising over 100,000 high-quality samples with realistic object shadows and reflections.<n>By constructing object-background pairs from video frames with off-the-shelf vision models, the labor costs of data acquisition can be significantly reduced.<n>To avoid generating shape-like artifacts and unintended content, we propose Object-Background Guidance.<n>We present OmniEraser, a novel method that seamlessly removes objects and their visual effects using only object masks as input.
  arXiv  Detail & Related papers  (2025-01-13T15:12:40Z)
• 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)
• 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)
• Magicremover: Tuning-free Text-guided Image inpainting with Diffusion Models [24.690863845885367]
  We propose MagicRemover, a tuning-free method that leverages the powerful diffusion models for text-guided image inpainting. We introduce an attention guidance strategy to constrain the sampling process of diffusion models, enabling the erasing of instructed areas and the restoration of occluded content.
  arXiv  Detail & Related papers  (2023-10-04T14:34:11Z)
• OR-NeRF: Object Removing from 3D Scenes Guided by Multiview Segmentation with Neural Radiance Fields [53.32527220134249]
  The emergence of Neural Radiance Fields (NeRF) for novel view synthesis has increased interest in 3D scene editing. Current methods face challenges such as time-consuming object labeling, limited capability to remove specific targets, and compromised rendering quality after removal. This paper proposes a novel object-removing pipeline, named OR-NeRF, that can remove objects from 3D scenes with user-given points or text prompts on a single view.
  arXiv  Detail & Related papers  (2023-05-17T18:18:05Z)
• Self-Supervised Video Object Segmentation via Cutout Prediction and Tagging [117.73967303377381]
  We propose a novel self-supervised Video Object (VOS) approach that strives to achieve better object-background discriminability. Our approach is based on a discriminative learning loss formulation that takes into account both object and background information. Our proposed approach, CT-VOS, achieves state-of-the-art results on two challenging benchmarks: DAVIS-2017 and Youtube-VOS.
  arXiv  Detail & Related papers  (2022-04-22T17:53:27Z)
• Thin-Plate Spline Motion Model for Image Animation [9.591298403129532]
  Image animation brings life to the static object in the source image according to the driving video. Recent works attempt to perform motion transfer on arbitrary objects through unsupervised methods without using a priori knowledge. It remains a significant challenge for current unsupervised methods when there is a large pose gap between the objects in the source and driving images.
  arXiv  Detail & Related papers  (2022-03-27T18:40:55Z)

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.