Let Real Images be as a Judger, Spotting Fake Images Synthesized with Generative Models

arXiv:2403.16513v1 Announce Type: new
Abstract: In the last few years, generative models have shown their powerful capabilities in synthesizing realistic images in both quality and diversity (i.e., facial images, and natural subjects). Unfortunately, the artifact patterns in fake images synthesized by different generative models are inconsistent, leading to the failure of previous research that relied on spotting subtle differences between real and fake. In our preliminary experiments, we find that the artifacts in fake images always change with the development …

abstract artifact arxiv capabilities cs.cr cs.cv diversity fake generative generative models images natural patterns quality synthesized type