从检测到定位：面向完全合成与篡改图像的统一取证框架
From Detection to Localization: A Unified Forensics Framework for Fully Synthetic and Tampered Images
浏览论文内容
中文总结 AI 辅助
本研究针对生成式模型带来的图像篡改检测难题，提出统一多类取证框架，兼具分类与像素级定位能力，性能优于近期基准。
中文摘要 AI 辅助
生成式模型的快速发展显著加剧了篡改图像检测问题，因其能生成高度逼真的伪造品，凸显了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. 生成），这限制了区分和定位不同形式篡改的能力。为解决这些局限，本研究扩展了现有检测器，引入统一多类框架（真实 vs. 完全生成 vs. 篡改）。除了对图像真实性进行分类，该框架还集成了分割分支，以实现篡改区域的像素级定位。所提方法优于选定的近期基准，提供了一种高效解决方案，分类精度有所提升，且定位任务的交并比（IoU）得分更高。代码可在此 https URL 查找。
英文摘要
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.
发表机构
- University of Padova（帕多瓦大学）
机构由 AI 辅助整理，请以论文原文为准。
