统一检测真实、合成与篡改图像，并精确定位篡改区域。
From Detection to Localization: A Unified Forensics Framework for Fully Synthetic and Tampered Images
- 构建多类别框架，同时区分真实、完全合成和篡改图像。
- 引入分割分支，实现像素级篡改区域定位，IoU提升显著。
- 适合图像取证、安全审查等需要精准溯源的场景。
生成模型的快速发展加剧了图像伪造问题，因其能生成高度逼真的伪造内容，凸显多媒体取证的重要性。传统方法通常将图像篡改检测视为二分类任务（真实 vs. 合成），难以区分不同类型的篡改。为此，本文扩展现有检测器，提出统一的多类别框架（真实、完全合成、篡改）。该框架不仅实现图像真伪分类，还集成分割分支，支持像素级篡改区域定位。所提方法在多个基准上优于近期模型，在分类准确率和定位任务的交并比（IoU）上均有提升，提供高效解决方案。代码见：https://github.com/anngal01/From-Detection-to-Localization-A-Unified-Forensics-Framework-for-Fully-Synthetic-and-Tampered-Images。
原文摘要 · Abstract (English)
The rapid advancement of generative models has significantly worsened the problem of manipulated image detection, as these methods are capable of producing highly realistic forgeries, reinforcing the importance of multimedia forensics. Conventional approaches typically frame image manipulation detection as a binary classification task (real vs. generated), which limits the capability to distinguish and localize different forms of manipulation. To address these constraints, this work extends an existing detector by introducing a unified multiclass framework (real vs. fully generated vs. tampered). In addition to classifying image authenticity, the framework incorporates a segmentation branch to enable pixel-level localization of tampered regions. The proposed approach outperforms selected recent benchmarks, offering an efficient solution with improved classification accuracy and higher IoU scores for the localization task. Find the code at https://github.com/anngal01/From-Detection-to-Localization-A-Unified-Forensics-Framework-for-Fully-Synthetic-and-Tampered-Images.
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。