MaskSim: Detection of synthetic images by masked spectrum similarity analysis - Archive ouverte HAL
Communication Dans Un Congrès Année : 2024

MaskSim: Detection of synthetic images by masked spectrum similarity analysis

Résumé

Synthetic image generation methods have recently revolutionized the way in which visual content is created. This opens up creative opportunities but also presents challenges in preventing misinformation and crime. However, these methods leave traces in the Fourier spectrum that are invisible to humans, but can be detected by specialized tools. This paper describes a semi-white-box method for detecting synthetic images by revealing anomalous patterns in the spectral domain. Specifically, we train a mask to enhance the most discriminative frequencies and simultaneously train a reference pattern that resembles the patterns produced by a given generative method. The proposed method produces explainable results with state-of the-art performances and highlights cues that can be used as forensic evidence. Code is available at https://github.com/li-yanhao/masksim.
Fichier principal
Vignette du fichier
CVPR_masksim_20240426.pdf (17.48 Mo) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-04716636 , version 1 (01-10-2024)

Licence

Identifiants

Citer

Yanhao LI, Quentin Bammey, Marina Gardella, Tina Nikoukhah, Jean-Michel Morel, et al.. MaskSim: Detection of synthetic images by masked spectrum similarity analysis. 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), Jun 2024, Seattle, United States. pp.3855-3865, ⟨10.1109/CVPRW63382.2024.00390⟩. ⟨hal-04716636⟩
39 Consultations
11 Téléchargements

Altmetric

Partager

More