FreqBlender: Enhancing DeepFake Detection by Blending Frequency Knowledge

arXiv:2404.13872v1 Announce Type: new
Abstract: Generating synthetic fake faces, known as pseudo-fake faces, is an effective way to improve the generalization of DeepFake detection. Existing methods typically generate these faces by blending real or fake faces in color space. While these methods have shown promise, they overlook the simulation of frequency distribution in pseudo-fake faces, limiting the learning of generic forgery traces in-depth. To address this, this paper introduces {\em FreqBlender}, a new method that can generate pseudo-fake faces by …

abstract arxiv color cs.cv deepfake detection distribution fake generate knowledge simulation space synthetic the simulation type