ImgEdit

[ImgEdit: A Unified Image Editing Dataset and Benchmark](https://huggingface.co/papers/2505.20275)

# 🌍 Introduction
**ImgEdit** is a large-scale, high-quality image-editing dataset comprising 1.2 million carefully curated edit pairs, which contain both novel and complex single-turn edits, as well as challenging multi-turn tasks.

To ensure the data quality, we employ a multi-stage pipeline that integrates a cutting-edge vision-language model, a detection model, a segmentation model, alongside task-specific in-painting procedures and strict post-processing. ImgEdit surpasses existing datasets in both task novelty and data quality.

Using ImgEdit, we train **ImgEdit-E1**, an editing model using Vision Language Model to process the reference image and editing prompt, which outperforms existing open-source models on multiple tasks, highlighting the value of ImgEdit and model design.

For comprehensive evaluation, we introduce **ImgEdit-Bench**, a benchmark designed to evaluate image editing performance in terms of instruction adherence, editing quality, and detail preservation.
It includes a basic testsuite, a challenging single-turn suite, and a dedicated multi-turn suite.
We evaluate both open-source and proprietary models, as well as ImgEdit-E1.

# 📜 Citation
If you find our paper and code useful in your research, please consider giving a star ⭐ and citation 📝.
```bibtex
@article{ye2025imgedit,
title={ImgEdit: A Unified Image Editing Dataset and Benchmark},
author={Ye, Yang and He, Xianyi and Li, Zongjian and Lin, Bin and Yuan, Shenghai and Yan, Zhiyuan and Hou, Bohan and Yuan, Li},
journal={arXiv preprint arXiv:2505.20275},
year={2025}
}
```

[ImgEdit：统一图像编辑数据集与基准测试集](https://huggingface.co/papers/2505.20275)

# 🌍 引言
**ImgEdit（统一图像编辑数据集与基准测试集）** 是一个大规模、高质量的图像编辑数据集，包含120万条经过精心遴选的编辑样本对，涵盖新颖且复杂的单轮编辑任务，以及极具挑战性的多轮编辑任务。

为保障数据质量，我们采用了多阶段处理流程，整合了前沿视觉语言模型（Vision Language Model）、目标检测模型、语义分割模型，以及针对特定任务的图像修复（in-painting）流程与严格的后处理步骤。该数据集在任务新颖性与数据质量两方面均优于现有同类数据集。

我们基于ImgEdit训练得到**ImgEdit-E1**——一款通过视觉语言模型处理参考图像与编辑提示词的编辑模型，其在多项任务上的表现优于现有开源模型，凸显了ImgEdit数据集与模型设计的价值。

为实现全面的模型性能评估，我们推出了**ImgEdit-Bench**基准测试集，该测试集用于从指令遵循度、编辑质量与细节保留度三个维度评估图像编辑模型的性能。测试集包含基础测试套件、高难度单轮测试套件与专属多轮测试套件。我们对开源模型、闭源模型以及ImgEdit-E1均开展了评测。

# 📜 引用说明
若您的研究中用到了本文与配套代码，请为我们点亮⭐并引用该论文📝。
bibtex
@article{ye2025imgedit,
title={ImgEdit: A Unified Image Editing Dataset and Benchmark},
author={Ye, Yang and He, Xianyi and Li, Zongjian and Lin, Bin and Yuan, Shenghai and Yan, Zhiyuan and Hou, Bohan and Yuan, Li},
journal={arXiv preprint arXiv:2505.20275},
year={2025}
}

搜集汇总

背景与挑战

背景概述

ImgEdit是一个包含120万对高质量图像编辑对的大规模数据集，支持单轮和多轮编辑任务，采用多阶段流程确保数据质量，并用于训练和评估先进的图像编辑模型。