论文标题
Cyclegan没有棋盘伪影，用于伪造图像检测
CycleGAN without checkerboard artifacts for counter-forensics of fake-image detection
论文作者
论文摘要
在本文中，我们提出了一个新颖的自行车，而无需棋盘伪影，以进行伪造图像检测。图像操纵工具和深层图像合成技术（例如生成对抗网络（GAN）（GAN））的最新快速进步很容易生成假图像，因此检测操纵图像已成为一个紧迫的问题。大多数最先进的伪造检测方法都假定图像包括使用DNN生成的棋盘伪影。因此，我们提出了一个新颖的Cyclegan，而没有任何棋盘伪影，以首次使用伪造探测方法的反纹顺式制品，作为无需棋盘伪影的gan的一个例子。
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.
