DFREC recovers both the source and target faces from a deepfake image using identity segmentation and an identity-aware masked autoencoder.
Adaptive texture and spectrum clue mining for generalizable face forgery detection,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
DFREC: DeepFake Identity Recovery Based on Identity-aware Masked Autoencoder
DFREC recovers both the source and target faces from a deepfake image using identity segmentation and an identity-aware masked autoencoder.