A feature-space method that erases usable identity information from face images via learnable perturbations and a Face Revive Generator, rendering them ineffective for deepfake swapping while preserving visual quality.
Faceshifter: Towards high fidelity and occlusion aware face swapping
7 Pith papers cite this work. Polarity classification is still indexing.
7
Pith papers citing it
fields
cs.CV 7verdicts
UNVERDICTED 7representative citing papers
LivingSwap is the first video reference-guided face swapping model that uses keyframe conditioning and temporal stitching to preserve source video realism with high fidelity across long sequences.
Introduces the MMTT dataset of 152k manipulated facial images with masks and text descriptions, plus the ForgeryTalker model that jointly outputs localization masks and explanatory text, reporting 59.3 CIDEr and 73.67 IoU.
Lightweight fusion of WDF with SPSL or LBP cues into Xception improves AUC by 3.8-4.4% on FaceForensics++ and DFDC-Preview with negligible parameter overhead compared to larger frequency-based detectors.
DeFakerOne is a unified foundation model for joint image-level fake image detection and pixel-level localization that reports SOTA results on 39 detection and 9 localization benchmarks.
VRAG-DFD uses RAG to retrieve forgery knowledge and RL-based training to build critical reasoning in MLLMs, delivering state-of-the-art generalization on deepfake detection tasks.
M3D-Net reconstructs 3D facial features from RGB images and fuses them with RGB features through attention-based modules to achieve claimed state-of-the-art deepfake detection.
citing papers explorer
-
ID-Eraser: Proactive Defense Against Face Swapping via Identity Perturbation
A feature-space method that erases usable identity information from face images via learnable perturbations and a Face Revive Generator, rendering them ineffective for deepfake swapping while preserving visual quality.
-
Preserving Source Video Realism: High-Fidelity Face Swapping for Cinematic Quality
LivingSwap is the first video reference-guided face swapping model that uses keyframe conditioning and temporal stitching to preserve source video realism with high fidelity across long sequences.
-
Generating Attribution Reports for Manipulated Facial Images: A Dataset and Baseline
Introduces the MMTT dataset of 152k manipulated facial images with masks and text descriptions, plus the ForgeryTalker model that jointly outputs localization masks and explanatory text, reporting 59.3 CIDEr and 73.67 IoU.
-
Lightweight Complementary-Cue Fusion for Robust Video Face Forgery Detection
Lightweight fusion of WDF with SPSL or LBP cues into Xception improves AUC by 3.8-4.4% on FaceForensics++ and DFDC-Preview with negligible parameter overhead compared to larger frequency-based detectors.
-
Venus-DeFakerOne: Unified Fake Image Detection & Localization
DeFakerOne is a unified foundation model for joint image-level fake image detection and pixel-level localization that reports SOTA results on 39 detection and 9 localization benchmarks.
-
VRAG-DFD: Verifiable Retrieval-Augmentation for MLLM-based Deepfake Detection
VRAG-DFD uses RAG to retrieve forgery knowledge and RL-based training to build critical reasoning in MLLMs, delivering state-of-the-art generalization on deepfake detection tasks.
-
M3D-Net: Multi-Modal 3D Facial Feature Reconstruction Network for Deepfake Detection
M3D-Net reconstructs 3D facial features from RGB images and fuses them with RGB features through attention-based modules to achieve claimed state-of-the-art deepfake detection.