# Erase Diffusion: Empowering Object Removal Through Calibrating Diffusion Pathways

arXiv: https://arxiv.org/abs/2503.07026 · HTML: https://mlsanity.com/paper/2503.07026/

## Key facts

- Cited by 18 papers in the map (data through 14 Oct 2026).
- Builds on 13 of its 15 references that are in the map.
- First posted on arXiv 10 Mar 2025.

## Builds on (most cited first, 13 of 13)

- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [Denoising Diffusion Implicit Models](https://mlsanity.com/paper/2010.02502/) (2020)
- [Masked-attention Mask Transformer for Universal Image Segmentation](https://mlsanity.com/paper/2112.01527/) (2021)
- [DPM-Solver: A Fast ODE Solver for Diffusion Probabilistic Model Sampling in Around 10 Steps](https://mlsanity.com/paper/2206.00927/) (2022)
- [Resolution-robust Large Mask Inpainting with Fourier Convolutions](https://mlsanity.com/paper/2109.07161/) (2021)
- [NIMA: Neural Image Assessment](https://mlsanity.com/paper/1709.05424/) (2017)
- [Large Scale Image Completion via Co-Modulated Generative Adversarial Networks](https://mlsanity.com/paper/2103.10428/) (2021)
- [A Task is Worth One Word: Learning with Task Prompts for High-Quality Versatile Image Inpainting](https://mlsanity.com/paper/2312.03594/) (2023)
- [FSS-1000: A 1000-Class Dataset for Few-Shot Segmentation](https://mlsanity.com/paper/1907.12347/) (2019)
- [Inst-Inpaint: Instructing to Remove Objects with Diffusion Models](https://mlsanity.com/paper/2304.03246/) (2023)
- [Deep Animation Video Interpolation in the Wild](https://mlsanity.com/paper/2104.02495/) (2021)
- [ViTMatte: Boosting Image Matting with Pretrained Plain Vision Transformers](https://mlsanity.com/paper/2305.15272/) (2023)

## Built on by (most cited first, 18 of 18)

- [EffectErase: Joint Video Object Removal and Insertion for High-Quality Effect Erasing](https://mlsanity.com/paper/2603.19224/) (2026)
- [Diffusion Probe: Generated Image Result Prediction Using CNN Probes](https://mlsanity.com/paper/2602.23783/) (2026)
- [Precise Object and Effect Removal with Adaptive Target-Aware Attention](https://mlsanity.com/paper/2505.22636/) (2025)
- [TC-Pad'e: Trajectory-Consistent Pad'e Approximation for Diffusion Acceleration](https://mlsanity.com/paper/2603.02943/) (2026)
- [simpleposter: A simple baseline for product poster generation](https://mlsanity.com/paper/2605.08784/) (2026)
- [RePainter: Empowering E-commerce Object Removal via Spatial-matting Reinforcement Learning](https://mlsanity.com/paper/2510.07721/) (2025)
- [MetaVideoAgent: Automated Video-Agent Evolution for Long-Form Video Understanding](https://mlsanity.com/paper/2608.04587/) (2026)
- [Beyond Fixed Anchors: Precisely Erasing Concepts with Sibling Exclusive Counterparts](https://mlsanity.com/paper/2510.16342/) (2025)
- [FlashClear: Ultra-Fast Image Content Removal via Efficient Step Distillation and Feature Caching](https://mlsanity.com/paper/2605.09003/) (2026)
- [DORS: Dynamic Attention Routing for Diffusion-based Object Removal in Dense Scenes](https://mlsanity.com/paper/2607.16656/) (2026)
- [MILD: Multi-Layer Diffusion Strategy for Complex and Precise Multi-IP Aware Human Erasing](https://mlsanity.com/paper/2508.06543/) (2025)
- [Generative Image Restoration and Super-Resolution using Physics-Informed Synthetic Data for Scanning Tunneling Microscopy](https://mlsanity.com/paper/2510.25921/) (2025)
- [EraseLoRA: MLLM-Driven Foreground Exclusion and Background Subtype Aggregation for Dataset-Free Object Removal](https://mlsanity.com/paper/2512.21545/) (2025)
- [You Only Erase Once: Erasing Anything without Bringing Unexpected Content](https://mlsanity.com/paper/2603.27599/) (2026)
- [OSOR: One-Step Diffusion Inpainting for Effect-Aware Object Removal](https://mlsanity.com/paper/2606.28094/) (2026)
- [TurboClear: One-Step Object-Effect Removal via Region-Calibrated Distribution Matching and Fusion](https://mlsanity.com/paper/2608.01288/) (2026)
- [Fully Unleashing the Multimodal Attacker: Meta-Adaptive Jailbreaking of Vision-Language Models](https://mlsanity.com/paper/2608.27531/) (2026)
- [StreamErase: Towards Ultra-Fast Streaming Video Erasing](https://mlsanity.com/paper/2610.20137/) (2026)

## Abstract (arXiv)

Erase inpainting, or object removal, aims to precisely remove target objects within masked regions while preserving the overall consistency of the surrounding content. Despite diffusion-based methods have made significant strides in the field of image inpainting, challenges remain regarding the emergence of unexpected objects or artifacts. We assert that the inexact diffusion pathways established by existing standard optimization paradigms constrain the efficacy of object removal. To tackle these challenges, we propose a novel Erase Diffusion, termed EraDiff, aimed at unleashing the potential power of standard diffusion in the context of object removal. In contrast to standard diffusion, the EraDiff adapts both the optimization paradigm and the network to improve the coherence and elimination of the erasure results. We first introduce a Chain-Rectifying Optimization (CRO) paradigm, a sophisticated diffusion process specifically designed to align with the objectives of erasure. This paradigm establishes innovative diffusion transition pathways that simulate the gradual elimination of objects during optimization, allowing the model to accurately capture the intent of object removal. Furthermore, to mitigate deviations caused by artifacts during the sampling pathways, we develop a simple yet effective Self-Rectifying Attention (SRA) mechanism. The SRA calibrates the sampling pathways by altering self-attention activation, allowing the model to effectively bypass artifacts while further enhancing the coherence of the generated content. With this design, our proposed EraDiff achieves state-of-the-art performance on the OpenImages V5 dataset and demonstrates significant superiority in real-world scenarios.