构建首个针对图像修复伪造的大型评测基准，助力检测真实感篡改。
COCO-Inpaint: A Benchmark for Detecting and Localizing Inpainting-Based Image Manipulations
- 用6个顶尖修复模型生成高质量篡改图像，覆盖多种风格。
- 通过4种掩码策略生成23.8万张图像，涵盖丰富语义内容。
- 聚焦修复区与原图的内在不一致，适合研究伪造检测的学者。
图像编辑技术的进步虽带来高度逼真的内容生成，但也降低了任意篡改的门槛，引发多媒体真实性与安全性的担忧。现有图像篡改检测与定位（IMDL）方法多针对拼接或复制-移动伪造，而基于修复的篡改缺乏有效评测基准。为此，我们提出COCO-Inpaint，一个专为修复类篡改设计的综合性评测基准，包含三大贡献：1）由6个前沿修复模型生成的高质量修复样本；2）通过4种掩码生成策略结合可选文本引导实现多样化的生成场景；3）覆盖238,302张修复图像，具备丰富的语义多样性。该基准旨在揭示修复区域与真实区域间的内在不一致性，而非表面的语义异常（如物体形状）。我们还制定了严格的评估协议，采用三项标准指标对现有IMDL方法进行评测，揭示当前趋势与挑战。
原文摘要 · Abstract (English)
Recent advances in image manipulation have enabled highly photorealistic content generation, but also lowered the barrier to arbitrary editing, raising concerns about multimedia authenticity and security. Existing Image Manipulation Detection and Localization (IMDL) methods mainly target splicing or copy-move forgeries, while benchmarks for inpainting-based manipulations remain limited. To bridge this gap, we present COCO-Inpaint, a comprehensive benchmark specifically designed for inpainting detection and localization, with three key contributions: 1) High-quality inpainting samples generated by six state-of-the-art inpainting models, 2) Diverse generation scenarios enabled by four mask generation strategies with optional text guidance, and 3) Large-scale coverage of 238,302 inpainted images with rich semantic diversity. Our benchmark is constructed to highlight intrinsic inconsistencies between inpainted and authentic regions, rather than superficial semantic artifacts such as object shapes. We further establish a rigorous evaluation protocol with three standard metrics to benchmark existing IMDL methods and reveal current trends and challenges.
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。