In this paper, we propose a novel CycleGAN without checkerboard artifacts for counter-forensics of fake-image detection. Recent rapid advances in image manipulation tools and deep image synthesis techniques, such as Generative Adversarial Networks (GANs) have easily generated fake images, so detecting manipulated images has become an urgent issue. Most state-of-the-art forgery detection methods assume that images include checkerboard artifacts which are generated by using DNNs. Accordingly, we propose a novel CycleGAN without any checkerboard artifacts for counter-forensics of fake-mage detection methods for the first time, as an example of GANs without checkerboard artifacts.
翻译：在本文中,我们提出了一个新的没有格子板的CycroGAN小说,用于假图像检测的反法证。最近图像处理工具和深层图像合成技术(如General Aversarial Networks (GANs))的快速进步很容易生成假图像,因此检测被操纵的图像已成为一个紧迫问题。大多数最先进的伪造检测方法都假定图像包括使用DNS生成的格子物件。因此,我们首次提出了一个新的CycroGAN小说,没有任何格子板的假图像检测方法的反法证,例如没有格子板的GAN。
相关内容
微信扫码咨询专知VIP会员