构建首个针对指令式图像编辑的定位基准数据集
LocateEdit-Bench: A Benchmark for Instruction-Based Editing Localization
- 设计23.1万张指令驱动编辑图像数据集
- 覆盖4种主流编辑模型与3类常见修改类型
- 为新型伪造定位提供评测标准，适合安全与检测研究者
近期图像编辑技术实现了高度可控且语义感知的视觉内容修改，对篡改定位提出了全新挑战。现有AI伪造定位方法主要针对基于修补的篡改，难以应对最新的指令式编辑范式。为此，我们提出LocateEdit-Bench，一个包含231,000张编辑图像的大规模数据集，专门用于评估指令驱动图像编辑的定位方法。数据集整合了四种前沿编辑模型，涵盖三类常见编辑类型。我们对数据集进行了详尽分析，并制定了两种多指标评估协议，以衡量现有定位方法的表现。本工作为跟上图像编辑技术演进步伐奠定基础，助力未来伪造定位方法的发展。数据集将在论文被接受后开源。
原文摘要 · Abstract (English)
Recent advancements in image editing have enabled highly controllable and semantically-aware alteration of visual content, posing unprecedented challenges to manipulation localization. However, existing AI-generated forgery localization methods primarily focus on inpainting-based manipulations, making them ineffective against the latest instruction-based editing paradigms. To bridge this critical gap, we propose LocateEdit-Bench, a large-scale dataset comprising $231$K edited images, designed specifically to benchmark localization methods against instruction-driven image editing. Our dataset incorporates four cutting-edge editing models and covers three common edit types. We conduct a detailed analysis of the dataset and develop two multi-metric evaluation protocols to assess existing localization methods. Our work establishes a foundation to keep pace with the evolving landscape of image editing, thereby facilitating the development of effective methods for future forgery localization. Dataset will be open-sourced upon acceptance.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。