Zero-Shot Object Removal via Attention Masking, Latent Anchoring, and Refinement

arXiv:2609.28342 · cs.CV · Submitted 2026-09-23 · Read on arXiv

cs.CV

Submitted: 2026-09-23

Updated: 2026-09-23

Comments: Code available at https://github.com/arman-taghizadeh/zero-shot-diffusion-object-removal

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Consistency — 51× in this paper · explained in 3 episodes
• Alignment — 40× in this paper · explained in 1 episode
• Diffusion Model — 23× in this paper · explained in 8 episodes
• Diffusion Models — 10× in this paper · explained in 6 episodes
• Ablation — 7× in this paper · explained in 1 episode
• Embeddings — 7× in this paper · explained in 2 episodes
• Fine-Tuning — 7× in this paper · explained in 5 episodes
• International Conference on Machine Learning — 4× in this paper
• Conference on Computer Vision and Pattern Recognition — 3× in this paper
• Latent Space — 3× in this paper · explained in 7 episodes
• Trace — 3× in this paper · explained in 2 episodes
• Latent Diffusion Model — 2× in this paper · explained in 2 episodes
• Latent Diffusion Models — 2× in this paper · explained in 2 episodes
• Ablation Studies — 1× in this paper · explained in 1 episode
• Accuracy — 1× in this paper · explained in 1 episode
• Adam — 1× in this paper · explained in 2 episodes
• Adaptation — 1× in this paper · explained in 1 episode
• Bayesian Framework — 1× in this paper · explained in 3 episodes
• Distribution Shift — 1× in this paper · explained in 5 episodes
• Failure Modes — 1× in this paper · explained in 3 episodes
• Langevin Dynamics — 1× in this paper · explained in 2 episodes
• Regularization — 1× in this paper · explained in 3 episodes
• Segment Anything Model — 1× in this paper
• Segment Anything Model (SAM) — 1× in this paper · explained in 2 episodes

Sources

• Understanding the Impact of Negative Prompts: When and How Do They Take Effect?
• Gradpaint: Gradient-Guided Inpainting with Diffusion Models
• Classifier-Free Diffusion Guidance
• Plug-and-Play Diffusion Features for Text-Driven Image-to-Image Translation
• PANDORA: Pixel-wise Attention Dissolution and Latent Guidance for Zero-Shot Object Removal
• Uni-paint: A Unified Framework for Multimodal Image Inpainting with Pretrained Diffusion Model
• Magicremover: Tuning-free Text-guided Image inpainting with Diffusion Models
• ClickRemoval: An Interactive Open-Source Tool for Object Removal in Diffusion Models

Related papers

• Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
• AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
• Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
• MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
• TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
• A Survey on Efficient Vision-Language-Action Models