通过逆光照调和检测图像编辑区域，提升伪造识别精度。
Disharmony: Forensics using Reverse Lighting Harmonization
- 结合分割模型与调和数据，反向分析光照一致性
- 在多个调和数据集上优于现有检测方法
- 适合图像取证、虚拟试穿等场景的伪造检测
基于深度学习的内容生成与编辑技术迅速发展，催生了对图像真伪检测的需求。现有研究关注对象插入与背景调和，但多数检测模型忽视调和区域与背景的光照一致性问题。本文提出Disharmony网络，利用聚合的调和数据集与分割模型，通过逆向分析光照不一致来定位编辑区域。实验表明，该方法能有效识别人工或深度学习生成的编辑痕迹，尤其在虚拟试穿等复杂场景中表现优异，显著超越现有取证模型。本方法为调和对象的检测提供了新思路。
原文摘要 · Abstract (English)
Content generation and manipulation approaches based on deep learning methods have seen significant advancements, leading to an increased need for techniques to detect whether an image has been generated or edited. Another area of research focuses on the insertion and harmonization of objects within images. In this study, we explore the potential of using harmonization data in conjunction with a segmentation model to enhance the detection of edited image regions. These edits can be either manually crafted or generated using deep learning methods. Our findings demonstrate that this approach can effectively identify such edits. Existing forensic models often overlook the detection of harmonized objects in relation to the background, but our proposed Disharmony Network addresses this gap. By utilizing an aggregated dataset of harmonization techniques, our model outperforms existing forensic networks in identifying harmonized objects integrated into their backgrounds, and shows potential for detecting various forms of edits, including virtual try-on tasks.
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。