Fig 1 - uploaded by Gaobo Yang
Content may be subject to copyright.
Can you identify which face image is fake? (a) Real face images with different resolutions. (b) From left to right, fake face images generated by Glow, StyleGAN, PGGAN, Face2Face, StarGAN, respectively.
Source publication
With the proliferation of face image manipulation (FIM) techniques such as Face2Face and Deepfake, more fake face images are spreading over the internet, which brings serious challenges to public confidence. Face image forgery detection has made considerable progresses in exposing specific FIM, but it is still in scarcity of a robust fake face dete...
Context in source publication
Context 1
... well the facial expressions of the target video from a source actor [4]. For face attribute transfer, there also exist some generative models such as StarGAN [8], DIAT [15], CycleGAN [16], and IcGAN [17] to change facial attributes. Among them, StarGAN exploits a generator and a discriminator to obtain better visual quality than existing methods. Fig. 1 shows some examples of face images. Apparently, it is difficult for human eyes to differentiate those fake face images generated by FIM from real images. As we know, face image is an important form of non-verbal communication, from which we can perceive true information . If face images are intention- ally manipulated, it might bring ...
Similar publications
Saving money and time are very important in any research project, so we must find a way to decrease the time of the experiment. This method is called the accelerated life tests (ALT) under censored samples, which is a very efficient method to reduce time, which leads to a decrease in the cost of the experiment. This research project includes infere...
