2020/07/18 by Yuyang Qian, Yu-Yang Qian, Guojun Yin +8 · 130 citations
Computer Science · #Advanced Image Processing Techniques #Artificial intelligence #Computer Vision and Pattern Recognition (cs.CV) #Computer science #Computer vision #Digital Media Forensic Detection #Discrete cosine transform #FOS: Computer and information sciences #Face (sociological concept) #Frequency domain #Generative Adversarial Networks and Image Synthesis #Image (mathematics) #Machine learning #Pattern recognition (psychology) #Perception #Quality (philosophy) #cs.CV
paper · pdf · doi:10.48550/arxiv.2007.09355
published in arXiv (Cornell University) (Cornell University) · 21 pages, 9 figures, accepted as a POSTER at ECCV2020, UPDATE the appendix of the paper
openalex publication_date 2020/07/18 · arxiv created 2020/10/27 · arxiv updated 2020/10/28 · openalex created_date 2025/10/10 · openalex updated_date 2026/08/04
As realistic facial manipulation technologies have achieved remarkable progress, social concerns about potential malicious abuse of these technologies bring out an emerging research topic of face forgery detection. However, it is extremely challenging since recent advances are able to forge faces beyond the perception ability of human eyes, especially in compressed images and videos. We find that mining forgery patterns with the awareness of frequency could be a cure, as frequency provides a complementary viewpoint where either subtle forgery artifacts or compression errors could be well described. To introduce frequency into the face forgery detection, we propose a novel Frequency in Face Forgery Network (F3-Net), taking advantages of two different but complementary frequency-aware clues, 1) frequency-aware decomposed image components, and 2) local frequency statistics, to deeply mine the forgery patterns via our two-stream collaborative learning framework. We apply DCT as the applied frequency-domain transformation. Through comprehensive studies, we show that the proposed F3-Net significantly outperforms competing state-of-the-art methods on all compression qualities in the challenging FaceForensics++ dataset, especially wins a big lead upon low-quality media.